diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index ed1d6d2..9f5457a 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -29,12 +29,26 @@
 	  </address>
 	</affiliation>
       </author>
+      <author>
+	<firstname>Daniel</firstname>
+	<surname>Vetter</surname>
+	<contrib>Contributions all over the place</contrib>
+	<affiliation>
+	  <orgname>Intel Corporation</orgname>
+	  <address>
+	    <email>daniel.vetter@ffwll.ch</email>
+	  </address>
+	</affiliation>
+      </author>
     </authorgroup>
 
     <copyright>
       <year>2008-2009</year>
-      <year>2012</year>
+      <year>2013-2014</year>
       <holder>Intel Corporation</holder>
+    </copyright>
+    <copyright>
+      <year>2012</year>
       <holder>Laurent Pinchart</holder>
     </copyright>
 
@@ -60,7 +74,15 @@
 
 <toc></toc>
 
-  <!-- Introduction -->
+<part id="drmCore">
+  <title>DRM Core</title>
+  <partintro>
+    <para>
+      This first part of the DRM Developer's Guide documents core DRM code,
+      helper libraries for writting drivers and generic userspace interfaces
+      exposed by DRM drivers.
+    </para>
+  </partintro>
 
   <chapter id="drmIntroduction">
     <title>Introduction</title>
@@ -264,8 +286,8 @@
       <para>
         The <methodname>load</methodname> method is the driver and device
         initialization entry point. The method is responsible for allocating and
-        initializing driver private data, specifying supported performance
-        counters, performing resource allocation and mapping (e.g. acquiring
+	initializing driver private data, performing resource allocation and
+	mapping (e.g. acquiring
         clocks, mapping registers or allocating command buffers), initializing
         the memory manager (<xref linkend="drm-memory-management"/>), installing
         the IRQ handler (<xref linkend="drm-irq-registration"/>), setting up
@@ -295,7 +317,7 @@
 	their <methodname>load</methodname> method called with flags to 0.
       </para>
       <sect3>
-        <title>Driver Private &amp; Performance Counters</title>
+        <title>Driver Private Data</title>
         <para>
           The driver private hangs off the main
           <structname>drm_device</structname> structure and can be used for
@@ -307,14 +329,6 @@
           <structname>drm_device</structname>.<structfield>dev_priv</structfield>
           set to NULL when the driver is unloaded.
         </para>
-        <para>
-          DRM supports several counters which were used for rough performance
-          characterization. This stat counter system is deprecated and should not
-          be used. If performance monitoring is desired, the developer should
-          investigate and potentially enhance the kernel perf and tracing
-          infrastructure to export GPU related performance information for
-          consumption by performance monitoring tools and applications.
-        </para>
       </sect3>
       <sect3 id="drm-irq-registration">
         <title>IRQ Registration</title>
@@ -697,55 +711,16 @@
           respectively. The conversion is handled by the DRM core without any
           driver-specific support.
         </para>
-        <para>
-          Similar to global names, GEM file descriptors are also used to share GEM
-          objects across processes. They offer additional security: as file
-          descriptors must be explicitly sent over UNIX domain sockets to be shared
-          between applications, they can't be guessed like the globally unique GEM
-          names.
-        </para>
-        <para>
-          Drivers that support GEM file descriptors, also known as the DRM PRIME
-          API, must set the DRIVER_PRIME bit in the struct
-          <structname>drm_driver</structname>
-          <structfield>driver_features</structfield> field, and implement the
-          <methodname>prime_handle_to_fd</methodname> and
-          <methodname>prime_fd_to_handle</methodname> operations.
-        </para>
-        <para>
-          <synopsis>int (*prime_handle_to_fd)(struct drm_device *dev,
-                            struct drm_file *file_priv, uint32_t handle,
-                            uint32_t flags, int *prime_fd);
-  int (*prime_fd_to_handle)(struct drm_device *dev,
-                            struct drm_file *file_priv, int prime_fd,
-                            uint32_t *handle);</synopsis>
-          Those two operations convert a handle to a PRIME file descriptor and
-          vice versa. Drivers must use the kernel dma-buf buffer sharing framework
-          to manage the PRIME file descriptors.
-        </para>
-        <para>
-          While non-GEM drivers must implement the operations themselves, GEM
-          drivers must use the <function>drm_gem_prime_handle_to_fd</function>
-          and <function>drm_gem_prime_fd_to_handle</function> helper functions.
-          Those helpers rely on the driver
-          <methodname>gem_prime_export</methodname> and
-          <methodname>gem_prime_import</methodname> operations to create a dma-buf
-          instance from a GEM object (dma-buf exporter role) and to create a GEM
-          object from a dma-buf instance (dma-buf importer role).
-        </para>
-        <para>
-          <synopsis>struct dma_buf * (*gem_prime_export)(struct drm_device *dev,
-                                       struct drm_gem_object *obj,
-                                       int flags);
-  struct drm_gem_object * (*gem_prime_import)(struct drm_device *dev,
-                                              struct dma_buf *dma_buf);</synopsis>
-          These two operations are mandatory for GEM drivers that support DRM
-          PRIME.
-        </para>
-        <sect4>
-          <title>DRM PRIME Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_prime.c PRIME Helpers
-        </sect4>
+	<para>
+	  GEM also supports buffer sharing with dma-buf file descriptors through
+	  PRIME. GEM-based drivers must use the provided helpers functions to
+	  implement the exporting and importing correctly. See <xref linkend="drm-prime-support" />.
+	  Since sharing file descriptors is inherently more secure than the
+	  easily guessable and global GEM names it is the preferred buffer
+	  sharing mechanism. Sharing buffers through GEM names is only supported
+	  for legacy userspace. Furthermore PRIME also allows cross-device
+	  buffer sharing since it is based on dma-bufs.
+	</para>
       </sect3>
       <sect3 id="drm-gem-objects-mapping">
         <title>GEM Objects Mapping</title>
@@ -830,62 +805,6 @@
         </para>
       </sect3>
       <sect3>
-        <title>Dumb GEM Objects</title>
-        <para>
-          The GEM API doesn't standardize GEM objects creation and leaves it to
-          driver-specific ioctls. While not an issue for full-fledged graphics
-          stacks that include device-specific userspace components (in libdrm for
-          instance), this limit makes DRM-based early boot graphics unnecessarily
-          complex.
-        </para>
-        <para>
-          Dumb GEM objects partly alleviate the problem by providing a standard
-          API to create dumb buffers suitable for scanout, which can then be used
-          to create KMS frame buffers.
-        </para>
-        <para>
-          To support dumb GEM objects drivers must implement the
-          <methodname>dumb_create</methodname>,
-          <methodname>dumb_destroy</methodname> and
-          <methodname>dumb_map_offset</methodname> operations.
-        </para>
-        <itemizedlist>
-          <listitem>
-            <synopsis>int (*dumb_create)(struct drm_file *file_priv, struct drm_device *dev,
-                     struct drm_mode_create_dumb *args);</synopsis>
-            <para>
-              The <methodname>dumb_create</methodname> operation creates a GEM
-              object suitable for scanout based on the width, height and depth
-              from the struct <structname>drm_mode_create_dumb</structname>
-              argument. It fills the argument's <structfield>handle</structfield>,
-              <structfield>pitch</structfield> and <structfield>size</structfield>
-              fields with a handle for the newly created GEM object and its line
-              pitch and size in bytes.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>int (*dumb_destroy)(struct drm_file *file_priv, struct drm_device *dev,
-                      uint32_t handle);</synopsis>
-            <para>
-              The <methodname>dumb_destroy</methodname> operation destroys a dumb
-              GEM object created by <methodname>dumb_create</methodname>.
-            </para>
-          </listitem>
-          <listitem>
-            <synopsis>int (*dumb_map_offset)(struct drm_file *file_priv, struct drm_device *dev,
-                         uint32_t handle, uint64_t *offset);</synopsis>
-            <para>
-              The <methodname>dumb_map_offset</methodname> operation associates an
-              mmap fake offset with the GEM object given by the handle and returns
-              it. Drivers must use the
-              <function>drm_gem_create_mmap_offset</function> function to
-              associate the fake offset as described in
-              <xref linkend="drm-gem-objects-mapping"/>.
-            </para>
-          </listitem>
-        </itemizedlist>
-      </sect3>
-      <sect3>
         <title>Memory Coherency</title>
         <para>
           When mapped to the device or used in a command buffer, backing pages
@@ -924,7 +843,99 @@
           abstracted from the client in libdrm.
         </para>
       </sect3>
-    </sect2>
+      <sect3>
+        <title>GEM Function Reference</title>
+!Edrivers/gpu/drm/drm_gem.c
+      </sect3>
+      </sect2>
+      <sect2>
+	<title>VMA Offset Manager</title>
+!Pdrivers/gpu/drm/drm_vma_manager.c vma offset manager
+!Edrivers/gpu/drm/drm_vma_manager.c
+!Iinclude/drm/drm_vma_manager.h
+      </sect2>
+      <sect2 id="drm-prime-support">
+	<title>PRIME Buffer Sharing</title>
+	<para>
+	  PRIME is the cross device buffer sharing framework in drm, originally
+	  created for the OPTIMUS range of multi-gpu platforms. To userspace
+	  PRIME buffers are dma-buf based file descriptors.
+	</para>
+	<sect3>
+	  <title>Overview and Driver Interface</title>
+	  <para>
+	    Similar to GEM global names, PRIME file descriptors are
+	    also used to share buffer objects across processes. They offer
+	    additional security: as file descriptors must be explicitly sent over
+	    UNIX domain sockets to be shared between applications, they can't be
+	    guessed like the globally unique GEM names.
+	  </para>
+	  <para>
+	    Drivers that support the PRIME
+	    API must set the DRIVER_PRIME bit in the struct
+	    <structname>drm_driver</structname>
+	    <structfield>driver_features</structfield> field, and implement the
+	    <methodname>prime_handle_to_fd</methodname> and
+	    <methodname>prime_fd_to_handle</methodname> operations.
+	  </para>
+	  <para>
+	    <synopsis>int (*prime_handle_to_fd)(struct drm_device *dev,
+			  struct drm_file *file_priv, uint32_t handle,
+			  uint32_t flags, int *prime_fd);
+int (*prime_fd_to_handle)(struct drm_device *dev,
+			  struct drm_file *file_priv, int prime_fd,
+			  uint32_t *handle);</synopsis>
+	    Those two operations convert a handle to a PRIME file descriptor and
+	    vice versa. Drivers must use the kernel dma-buf buffer sharing framework
+	    to manage the PRIME file descriptors. Similar to the mode setting
+	    API PRIME is agnostic to the underlying buffer object manager, as
+	    long as handles are 32bit unsinged integers.
+	  </para>
+	  <para>
+	    While non-GEM drivers must implement the operations themselves, GEM
+	    drivers must use the <function>drm_gem_prime_handle_to_fd</function>
+	    and <function>drm_gem_prime_fd_to_handle</function> helper functions.
+	    Those helpers rely on the driver
+	    <methodname>gem_prime_export</methodname> and
+	    <methodname>gem_prime_import</methodname> operations to create a dma-buf
+	    instance from a GEM object (dma-buf exporter role) and to create a GEM
+	    object from a dma-buf instance (dma-buf importer role).
+	  </para>
+	  <para>
+	    <synopsis>struct dma_buf * (*gem_prime_export)(struct drm_device *dev,
+				     struct drm_gem_object *obj,
+				     int flags);
+struct drm_gem_object * (*gem_prime_import)(struct drm_device *dev,
+					    struct dma_buf *dma_buf);</synopsis>
+	    These two operations are mandatory for GEM drivers that support
+	    PRIME.
+	  </para>
+	</sect3>
+        <sect3>
+          <title>PRIME Helper Functions</title>
+!Pdrivers/gpu/drm/drm_prime.c PRIME Helpers
+        </sect3>
+      </sect2>
+      <sect2>
+	<title>PRIME Function References</title>
+!Edrivers/gpu/drm/drm_prime.c
+      </sect2>
+      <sect2>
+	<title>DRM MM Range Allocator</title>
+	<sect3>
+	  <title>Overview</title>
+!Pdrivers/gpu/drm/drm_mm.c Overview
+	</sect3>
+	<sect3>
+	  <title>LRU Scan/Eviction Support</title>
+!Pdrivers/gpu/drm/drm_mm.c lru scan roaster
+	</sect3>
+      </sect2>
+      <sect2>
+	<title>DRM MM Range Allocator Function References</title>
+!Edrivers/gpu/drm/drm_mm.c
+!Iinclude/drm/drm_mm.h
+      </sect2>
   </sect1>
 
   <!-- Internals: mode setting -->
@@ -953,6 +964,11 @@
       </listitem>
     </itemizedlist>
     <sect2>
+      <title>Display Modes Function Reference</title>
+!Iinclude/drm/drm_modes.h
+!Edrivers/gpu/drm/drm_modes.c
+    </sect2>
+    <sect2>
       <title>Frame Buffer Creation</title>
       <synopsis>struct drm_framebuffer *(*fb_create)(struct drm_device *dev,
 				     struct drm_file *file_priv,
@@ -968,9 +984,11 @@
         Frame buffers rely on the underneath memory manager for low-level memory
         operations. When creating a frame buffer applications pass a memory
         handle (or a list of memory handles for multi-planar formats) through
-        the <parameter>drm_mode_fb_cmd2</parameter> argument. This document
-        assumes that the driver uses GEM, those handles thus reference GEM
-        objects.
+	the <parameter>drm_mode_fb_cmd2</parameter> argument. For drivers using
+	GEM as their userspace buffer management interface this would be a GEM
+	handle.  Drivers are however free to use their own backing storage object
+	handles, e.g. vmwgfx directly exposes special TTM handles to userspace
+	and so expects TTM handles in the create ioctl and not GEM handles.
       </para>
       <para>
         Drivers must first validate the requested frame buffer parameters passed
@@ -992,7 +1010,7 @@
       </para>
 
       <para>
-	The initailization of the new framebuffer instance is finalized with a
+	The initialization of the new framebuffer instance is finalized with a
 	call to <function>drm_framebuffer_init</function> which takes a pointer
 	to DRM frame buffer operations (struct
 	<structname>drm_framebuffer_funcs</structname>). Note that this function
@@ -1042,7 +1060,7 @@
       <para>
 	The lifetime of a drm framebuffer is controlled with a reference count,
 	drivers can grab additional references with
-	<function>drm_framebuffer_reference</function> </para> and drop them
+	<function>drm_framebuffer_reference</function>and drop them
 	again with <function>drm_framebuffer_unreference</function>. For
 	driver-private framebuffers for which the last reference is never
 	dropped (e.g. for the fbdev framebuffer when the struct
@@ -1050,6 +1068,72 @@
 	helper struct) drivers can manually clean up a framebuffer at module
 	unload time with
 	<function>drm_framebuffer_unregister_private</function>.
+      </para>
+    </sect2>
+    <sect2>
+      <title>Dumb Buffer Objects</title>
+      <para>
+	The KMS API doesn't standardize backing storage object creation and
+	leaves it to driver-specific ioctls. Furthermore actually creating a
+	buffer object even for GEM-based drivers is done through a
+	driver-specific ioctl - GEM only has a common userspace interface for
+	sharing and destroying objects. While not an issue for full-fledged
+	graphics stacks that include device-specific userspace components (in
+	libdrm for instance), this limit makes DRM-based early boot graphics
+	unnecessarily complex.
+      </para>
+      <para>
+        Dumb objects partly alleviate the problem by providing a standard
+        API to create dumb buffers suitable for scanout, which can then be used
+        to create KMS frame buffers.
+      </para>
+      <para>
+        To support dumb objects drivers must implement the
+        <methodname>dumb_create</methodname>,
+        <methodname>dumb_destroy</methodname> and
+        <methodname>dumb_map_offset</methodname> operations.
+      </para>
+      <itemizedlist>
+        <listitem>
+          <synopsis>int (*dumb_create)(struct drm_file *file_priv, struct drm_device *dev,
+                   struct drm_mode_create_dumb *args);</synopsis>
+          <para>
+            The <methodname>dumb_create</methodname> operation creates a driver
+	    object (GEM or TTM handle) suitable for scanout based on the
+	    width, height and depth from the struct
+	    <structname>drm_mode_create_dumb</structname> argument. It fills the
+	    argument's <structfield>handle</structfield>,
+	    <structfield>pitch</structfield> and <structfield>size</structfield>
+	    fields with a handle for the newly created object and its line
+            pitch and size in bytes.
+          </para>
+        </listitem>
+        <listitem>
+          <synopsis>int (*dumb_destroy)(struct drm_file *file_priv, struct drm_device *dev,
+                    uint32_t handle);</synopsis>
+          <para>
+            The <methodname>dumb_destroy</methodname> operation destroys a dumb
+            object created by <methodname>dumb_create</methodname>.
+          </para>
+        </listitem>
+        <listitem>
+          <synopsis>int (*dumb_map_offset)(struct drm_file *file_priv, struct drm_device *dev,
+                       uint32_t handle, uint64_t *offset);</synopsis>
+          <para>
+            The <methodname>dumb_map_offset</methodname> operation associates an
+            mmap fake offset with the object given by the handle and returns
+            it. Drivers must use the
+            <function>drm_gem_create_mmap_offset</function> function to
+            associate the fake offset as described in
+            <xref linkend="drm-gem-objects-mapping"/>.
+          </para>
+        </listitem>
+      </itemizedlist>
+      <para>
+        Note that dumb objects may not be used for gpu acceleration, as has been
+	attempted on some ARM embedded platforms. Such drivers really must have
+	a hardware-specific ioctl to allocate suitable buffer objects.
+      </para>
     </sect2>
     <sect2>
       <title>Output Polling</title>
@@ -1130,8 +1214,11 @@
             This operation is called with the mode config lock held.
           </para>
           <note><para>
-            FIXME: How should set_config interact with DPMS? If the CRTC is
-            suspended, should it be resumed?
+	    Note that the drm core has no notion of restoring the mode setting
+	    state after resume, since all resume handling is in the full
+	    responsibility of the driver. The common mode setting helper library
+	    though provides a helper which can be used for this:
+	    <function>drm_helper_resume_force_mode</function>.
           </para></note>
         </sect4>
         <sect4>
@@ -2134,7 +2221,7 @@
             set the <structfield>display_info</structfield>
             <structfield>width_mm</structfield> and
             <structfield>height_mm</structfield> fields if they haven't been set
-            already (for instance at initilization time when a fixed-size panel is
+            already (for instance at initialization time when a fixed-size panel is
             attached to the connector). The mode <structfield>width_mm</structfield>
             and <structfield>height_mm</structfield> fields are only used internally
             during EDID parsing and should not be set when creating modes manually.
@@ -2196,10 +2283,15 @@
 !Edrivers/gpu/drm/drm_flip_work.c
     </sect2>
     <sect2>
-      <title>VMA Offset Manager</title>
-!Pdrivers/gpu/drm/drm_vma_manager.c vma offset manager
-!Edrivers/gpu/drm/drm_vma_manager.c
-!Iinclude/drm/drm_vma_manager.h
+      <title>HDMI Infoframes Helper Reference</title>
+      <para>
+	Strictly speaking this is not a DRM helper library but generally useable
+	by any driver interfacing with HDMI outputs like v4l or alsa drivers.
+	But it nicely fits into the overall topic of mode setting helper
+	libraries and hence is also included here.
+      </para>
+!Iinclude/linux/hdmi.h
+!Edrivers/video/hdmi.c
     </sect2>
   </sect1>
 
@@ -2561,42 +2653,44 @@
       </para>
     </sect2>
   </sect1>
-
   <sect1>
-    <title>Command submission &amp; fencing</title>
+    <title>Legacy Support Code</title>
     <para>
-      This should cover a few device-specific command submission
-      implementations.
+      The section very brievely covers some of the old legacy support code which
+      is only used by old DRM drivers which have done a so-called shadow-attach
+      to the underlying device instead of registering as a real driver. This
+      also includes some of the old generic buffer mangement and command
+      submission code. Do not use any of this in new and modern drivers.
     </para>
-  </sect1>
 
-  <!-- Internals: suspend/resume -->
+    <sect2>
+      <title>Legacy Suspend/Resume</title>
+      <para>
+	The DRM core provides some suspend/resume code, but drivers wanting full
+	suspend/resume support should provide save() and restore() functions.
+	These are called at suspend, hibernate, or resume time, and should perform
+	any state save or restore required by your device across suspend or
+	hibernate states.
+      </para>
+      <synopsis>int (*suspend) (struct drm_device *, pm_message_t state);
+  int (*resume) (struct drm_device *);</synopsis>
+      <para>
+	Those are legacy suspend and resume methods which
+	<emphasis>only</emphasis> work with the legacy shadow-attach driver
+	registration functions. New driver should use the power management
+	interface provided by their bus type (usually through
+	the struct <structname>device_driver</structname> dev_pm_ops) and set
+	these methods to NULL.
+      </para>
+    </sect2>
 
-  <sect1>
-    <title>Suspend/Resume</title>
-    <para>
-      The DRM core provides some suspend/resume code, but drivers wanting full
-      suspend/resume support should provide save() and restore() functions.
-      These are called at suspend, hibernate, or resume time, and should perform
-      any state save or restore required by your device across suspend or
-      hibernate states.
-    </para>
-    <synopsis>int (*suspend) (struct drm_device *, pm_message_t state);
-int (*resume) (struct drm_device *);</synopsis>
-    <para>
-      Those are legacy suspend and resume methods. New driver should use the
-      power management interface provided by their bus type (usually through
-      the struct <structname>device_driver</structname> dev_pm_ops) and set
-      these methods to NULL.
-    </para>
-  </sect1>
-
-  <sect1>
-    <title>DMA services</title>
-    <para>
-      This should cover how DMA mapping etc. is supported by the core.
-      These functions are deprecated and should not be used.
-    </para>
+    <sect2>
+      <title>Legacy DMA Services</title>
+      <para>
+	This should cover how DMA mapping etc. is supported by the core.
+	These functions are deprecated and should not be used.
+      </para>
+    </sect2>
   </sect1>
   </chapter>
 
@@ -2658,8 +2752,8 @@
         DRM core provides multiple character-devices for user-space to use.
         Depending on which device is opened, user-space can perform a different
         set of operations (mainly ioctls). The primary node is always created
-        and called <term>card&lt;num&gt;</term>. Additionally, a currently
-        unused control node, called <term>controlD&lt;num&gt;</term> is also
+        and called card&lt;num&gt;. Additionally, a currently
+        unused control node, called controlD&lt;num&gt; is also
         created. The primary node provides all legacy operations and
         historically was the only interface used by userspace. With KMS, the
         control node was introduced. However, the planned KMS control interface
@@ -2674,21 +2768,21 @@
         nodes were introduced. Render nodes solely serve render clients, that
         is, no modesetting or privileged ioctls can be issued on render nodes.
         Only non-global rendering commands are allowed. If a driver supports
-        render nodes, it must advertise it via the <term>DRIVER_RENDER</term>
+        render nodes, it must advertise it via the DRIVER_RENDER
         DRM driver capability. If not supported, the primary node must be used
         for render clients together with the legacy drmAuth authentication
         procedure.
       </para>
       <para>
         If a driver advertises render node support, DRM core will create a
-        separate render node called <term>renderD&lt;num&gt;</term>. There will
+        separate render node called renderD&lt;num&gt;. There will
         be one render node per device. No ioctls except  PRIME-related ioctls
-        will be allowed on this node. Especially <term>GEM_OPEN</term> will be
+        will be allowed on this node. Especially GEM_OPEN will be
         explicitly prohibited. Render nodes are designed to avoid the
         buffer-leaks, which occur if clients guess the flink names or mmap
         offsets on the legacy interface. Additionally to this basic interface,
         drivers must mark their driver-dependent render-only ioctls as
-        <term>DRM_RENDER_ALLOW</term> so render clients can use them. Driver
+        DRM_RENDER_ALLOW so render clients can use them. Driver
         authors must be careful not to allow any privileged ioctls on render
         nodes.
       </para>
@@ -2749,15 +2843,73 @@
     </sect1>
 
   </chapter>
+</part>
+<part id="drmDrivers">
+  <title>DRM Drivers</title>
 
-  <!-- API reference -->
-
-  <appendix id="drmDriverApi">
-    <title>DRM Driver API</title>
+  <partintro>
     <para>
-      Include auto-generated API reference here (need to reference it
-      from paragraphs above too).
+      This second part of the DRM Developer's Guide documents driver code,
+      implementation details and also all the driver-specific userspace
+      interfaces. Especially since all hardware-acceleration interfaces to
+      userspace are driver specific for efficiency and other reasons these
+      interfaces can be rather substantial. Hence every driver has its own
+      chapter.
     </para>
-  </appendix>
+  </partintro>
 
+  <chapter id="drmI915">
+    <title>drm/i915 Intel GFX Driver</title>
+    <para>
+      The drm/i915 driver supports all (with the exception of some very early
+      models) integrated GFX chipsets with both Intel display and rendering
+      blocks. This excludes a set of SoC platforms with an SGX rendering unit,
+      those have basic support through the gma500 drm driver.
+    </para>
+    <sect1>
+      <title>Display Hardware Handling</title>
+      <para>
+        This section covers everything related to the display hardware including
+        the mode setting infrastructure, plane, sprite and cursor handling and
+        display, output probing and related topics.
+      </para>
+      <sect2>
+        <title>Mode Setting Infrastructure</title>
+        <para>
+          The i915 driver is thus far the only DRM driver which doesn't use the
+          common DRM helper code to implement mode setting sequences. Thus it
+          has its own tailor-made infrastructure for executing a display
+          configuration change.
+        </para>
+      </sect2>
+      <sect2>
+        <title>Plane Configuration</title>
+        <para>
+	  This section covers plane configuration and composition with the
+	  primary plane, sprites, cursors and overlays. This includes the
+	  infrastructure to do atomic vsync'ed updates of all this state and
+	  also tightly coupled topics like watermark setup and computation,
+	  framebuffer compression and panel self refresh.
+        </para>
+      </sect2>
+      <sect2>
+        <title>Output Probing</title>
+        <para>
+	  This section covers output probing and related infrastructure like the
+	  hotplug interrupt storm detection and mitigation code. Note that the
+	  i915 driver still uses most of the common DRM helper code for output
+	  probing, so those sections fully apply.
+        </para>
+      </sect2>
+    </sect1>
+
+    <sect1>
+      <title>Memory Management and Command Submission</title>
+      <para>
+	This sections covers all things related to the GEM implementation in the
+	i915 driver.
+      </para>
+    </sect1>
+  </chapter>
+</part>
 </book>
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index e6b72d3..68c0f51 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -124,12 +124,11 @@
 Updating on-disk metadata
 -------------------------
 
-On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is
-written.  If no such requests are made then commits will occur every
-second.  This means the cache behaves like a physical disk that has a
-write cache (the same is true of the thin-provisioning target).  If
-power is lost you may lose some recent writes.  The metadata should
-always be consistent in spite of any crash.
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second.  This
+means the cache behaves like a physical disk that has a volatile write
+cache.  If power is lost you may lose some recent writes.  The metadata
+should always be consistent in spite of any crash.
 
 The 'dirty' state for a cache block changes far too frequently for us
 to keep updating it on the fly.  So we treat it as a hint.  In normal
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 8a7a3d4..05a27e9 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -116,6 +116,35 @@
 userspace daemon can use this to detect a situation where a new table
 already exceeds the threshold.
 
+A low water mark for the metadata device is maintained in the kernel and
+will trigger a dm event if free space on the metadata device drops below
+it.
+
+Updating on-disk metadata
+-------------------------
+
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second.  This
+means the thin-provisioning target behaves like a physical disk that has
+a volatile write cache.  If power is lost you may lose some recent
+writes.  The metadata should always be consistent in spite of any crash.
+
+If data space is exhausted the pool will either error or queue IO
+according to the configuration (see: error_if_no_space).  If metadata
+space is exhausted or a metadata operation fails: the pool will error IO
+until the pool is taken offline and repair is performed to 1) fix any
+potential inconsistencies and 2) clear the flag that imposes repair.
+Once the pool's metadata device is repaired it may be resized, which
+will allow the pool to return to normal operation.  Note that if a pool
+is flagged as needing repair, the pool's data and metadata devices
+cannot be resized until repair is performed.  It should also be noted
+that when the pool's metadata space is exhausted the current metadata
+transaction is aborted.  Given that the pool will cache IO whose
+completion may have already been acknowledged to upper IO layers
+(e.g. filesystem) it is strongly suggested that consistency checks
+(e.g. fsck) be performed on those layers when repair of the pool is
+required.
+
 Thin provisioning
 -----------------
 
@@ -258,10 +287,9 @@
 	should register for the event and then check the target's status.
 
     held metadata root:
-	The location, in sectors, of the metadata root that has been
+	The location, in blocks, of the metadata root that has been
 	'held' for userspace read access.  '-' indicates there is no
-	held root.  This feature is not yet implemented so '-' is
-	always returned.
+	held root.
 
     discard_passdown|no_discard_passdown
 	Whether or not discards are actually being passed down to the
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index a6a352c..5992dce 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -21,9 +21,9 @@
     must appear in the same order as the output clocks.
   - #clock-cells: Must be 1
   - clock-output-names: The name of the clocks as free-form strings
-  - renesas,indices: Indices of the gate clocks into the group (0 to 31)
+  - renesas,clock-indices: Indices of the gate clocks into the group (0 to 31)
 
-The clocks, clock-output-names and renesas,indices properties contain one
+The clocks, clock-output-names and renesas,clock-indices properties contain one
 entry per gate clock. The MSTP groups are sparsely populated. Unimplemented
 gate clocks must not be declared.
 
diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
index 68b83ec..ee9be99 100644
--- a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
@@ -1,12 +1,16 @@
 * Freescale Smart Direct Memory Access (SDMA) Controller for i.MX
 
 Required properties:
-- compatible : Should be "fsl,imx31-sdma", "fsl,imx31-to1-sdma",
-  "fsl,imx31-to2-sdma", "fsl,imx35-sdma", "fsl,imx35-to1-sdma",
-  "fsl,imx35-to2-sdma", "fsl,imx51-sdma", "fsl,imx53-sdma" or
-  "fsl,imx6q-sdma". The -to variants should be preferred since they
-  allow to determnine the correct ROM script addresses needed for
-  the driver to work without additional firmware.
+- compatible : Should be one of
+      "fsl,imx25-sdma"
+      "fsl,imx31-sdma", "fsl,imx31-to1-sdma", "fsl,imx31-to2-sdma"
+      "fsl,imx35-sdma", "fsl,imx35-to1-sdma", "fsl,imx35-to2-sdma"
+      "fsl,imx51-sdma"
+      "fsl,imx53-sdma"
+      "fsl,imx6q-sdma"
+  The -to variants should be preferred since they allow to determnine the
+  correct ROM script addresses needed for the driver to work without additional
+  firmware.
 - reg : Should contain SDMA registers location and length
 - interrupts : Should contain SDMA interrupt
 - #dma-cells : Must be <3>.
diff --git a/Documentation/devicetree/bindings/net/opencores-ethoc.txt b/Documentation/devicetree/bindings/net/opencores-ethoc.txt
new file mode 100644
index 0000000..2dc127c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/opencores-ethoc.txt
@@ -0,0 +1,22 @@
+* OpenCores MAC 10/100 Mbps
+
+Required properties:
+- compatible: Should be "opencores,ethoc".
+- reg: two memory regions (address and length),
+  first region is for the device registers and descriptor rings,
+  second is for the device packet memory.
+- interrupts: interrupt for the device.
+
+Optional properties:
+- clocks: phandle to refer to the clk used as per
+  Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Examples:
+
+	enet0: ethoc@fd030000 {
+		compatible = "opencores,ethoc";
+		reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
+		interrupts = <1>;
+		local-mac-address = [00 50 c2 13 6f 00];
+		clocks = <&osc>;
+        };
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
similarity index 98%
rename from Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
rename to Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
index 9e9e9ef..c119deb 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
@@ -1,4 +1,4 @@
-Broadcom Capri Pin Controller
+Broadcom BCM281xx Pin Controller
 
 This is a pin controller for the Broadcom BCM281xx SoC family, which includes
 BCM11130, BCM11140, BCM11351, BCM28145, and BCM28155 SoCs.
@@ -7,14 +7,14 @@
 
 Required Properties:
 
-- compatible:	Must be "brcm,capri-pinctrl".
+- compatible:	Must be "brcm,bcm11351-pinctrl"
 - reg:		Base address of the PAD Controller register block and the size
 		of the block.
 
 For example, the following is the bare minimum node:
 
 	pinctrl@35004800 {
-		compatible = "brcm,capri-pinctrl";
+		compatible = "brcm,bcm11351-pinctrl";
 		reg = <0x35004800 0x430>;
 	};
 
@@ -119,7 +119,7 @@
 Example:
 // pin controller node
 pinctrl@35004800 {
-	compatible = "brcm,capri-pinctrl";
+	compatible = "brcmbcm11351-pinctrl";
 	reg = <0x35004800 0x430>;
 
 	// pin configuration node
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index f3089d4..0cbe6ec 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -554,12 +554,6 @@
   not specified in the struct can_frame and therefore it is only valid in
   CANFD_MTU sized CAN FD frames.
 
-  As long as the payload length is <=8 the received CAN frames from CAN FD
-  capable CAN devices can be received and read by legacy sockets too. When
-  user-generated CAN FD frames have a payload length <=8 these can be send
-  by legacy CAN network interfaces too. Sending CAN FD frames with payload
-  length > 8 to a legacy CAN network interface returns an -EMSGSIZE error.
-
   Implementation hint for new CAN applications:
 
   To build a CAN FD aware application use struct canfd_frame as basic CAN
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 1404674..6fea79e 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -453,7 +453,7 @@
                         enabled previously with setsockopt() and 
                         the PACKET_COPY_THRESH option. 
 
-                        The number of frames than can be buffered to 
+                        The number of frames that can be buffered to
                         be read with recvfrom is limited like a normal socket.
                         See the SO_RCVBUF option in the socket (7) man page.
 
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 661d3c3..048c92b 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -21,26 +21,38 @@
 
 SO_TIMESTAMPING:
 
-Instructs the socket layer which kind of information is wanted. The
-parameter is an integer with some of the following bits set. Setting
-other bits is an error and doesn't change the current state.
+Instructs the socket layer which kind of information should be collected
+and/or reported.  The parameter is an integer with some of the following
+bits set. Setting other bits is an error and doesn't change the current
+state.
 
-SOF_TIMESTAMPING_TX_HARDWARE:  try to obtain send time stamp in hardware
-SOF_TIMESTAMPING_TX_SOFTWARE:  if SOF_TIMESTAMPING_TX_HARDWARE is off or
-                               fails, then do it in software
-SOF_TIMESTAMPING_RX_HARDWARE:  return the original, unmodified time stamp
-                               as generated by the hardware
-SOF_TIMESTAMPING_RX_SOFTWARE:  if SOF_TIMESTAMPING_RX_HARDWARE is off or
-                               fails, then do it in software
-SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp
-SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to
-                               the system time base
-SOF_TIMESTAMPING_SOFTWARE:     return system time stamp generated in
-                               software
+Four of the bits are requests to the stack to try to generate
+timestamps.  Any combination of them is valid.
 
-SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
-SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
-following control message:
+SOF_TIMESTAMPING_TX_HARDWARE:  try to obtain send time stamps in hardware
+SOF_TIMESTAMPING_TX_SOFTWARE:  try to obtain send time stamps in software
+SOF_TIMESTAMPING_RX_HARDWARE:  try to obtain receive time stamps in hardware
+SOF_TIMESTAMPING_RX_SOFTWARE:  try to obtain receive time stamps in software
+
+The other three bits control which timestamps will be reported in a
+generated control message.  If none of these bits are set or if none of
+the set bits correspond to data that is available, then the control
+message will not be generated:
+
+SOF_TIMESTAMPING_SOFTWARE:     report systime if available
+SOF_TIMESTAMPING_SYS_HARDWARE: report hwtimetrans if available
+SOF_TIMESTAMPING_RAW_HARDWARE: report hwtimeraw if available
+
+It is worth noting that timestamps may be collected for reasons other
+than being requested by a particular socket with
+SOF_TIMESTAMPING_[TR]X_(HARD|SOFT)WARE.  For example, most drivers that
+can generate hardware receive timestamps ignore
+SOF_TIMESTAMPING_RX_HARDWARE.  It is still a good idea to set that flag
+in case future drivers pay attention.
+
+If timestamps are reported, they will appear in a control message with
+cmsg_level==SOL_SOCKET, cmsg_type==SO_TIMESTAMPING, and a payload like
+this:
 
 struct scm_timestamping {
 	struct timespec systime;
diff --git a/MAINTAINERS b/MAINTAINERS
index 85b3dd8..b3fdb0f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -73,7 +73,8 @@
 	L: Mailing list that is relevant to this area
 	W: Web-page with status/info
 	Q: Patchwork web based patch tracking system site
-	T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit, topgit.
+	T: SCM tree type and location.
+	   Type is one of: git, hg, quilt, stgit, topgit
 	S: Status, one of the following:
 	   Supported:	Someone is actually paid to look after this.
 	   Maintained:	Someone actually looks after it.
@@ -473,7 +474,7 @@
 
 AGPGART DRIVER
 M:	David Airlie <airlied@linux.ie>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+T:	git git://people.freedesktop.org/~airlied/linux (part of drm maint)
 S:	Maintained
 F:	drivers/char/agp/
 F:	include/linux/agp*
@@ -538,7 +539,7 @@
 ALTERA UART/JTAG UART SERIAL DRIVERS
 M:	Tobias Klauser <tklauser@distanz.ch>
 L:	linux-serial@vger.kernel.org
-L:	nios2-dev@sopc.et.ntust.edu.tw (moderated for non-subscribers)
+L:	nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/tty/serial/altera_uart.c
 F:	drivers/tty/serial/altera_jtaguart.c
@@ -1612,11 +1613,11 @@
 F:	drivers/net/wireless/atmel*
 
 ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER
-M:      Bradley Grove <linuxdrivers@attotech.com>
-L:      linux-scsi@vger.kernel.org
-W:      http://www.attotech.com
-S:      Supported
-F:      drivers/scsi/esas2r
+M:	Bradley Grove <linuxdrivers@attotech.com>
+L:	linux-scsi@vger.kernel.org
+W:	http://www.attotech.com
+S:	Supported
+F:	drivers/scsi/esas2r
 
 AUDIT SUBSYSTEM
 M:	Eric Paris <eparis@redhat.com>
@@ -1737,6 +1738,7 @@
 BLACKFIN ARCHITECTURE
 M:	Steven Miao <realmz6@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net
+T:	git git://git.code.sf.net/p/adi-linux/code
 W:	http://blackfin.uclinux.org
 S:	Supported
 F:	arch/blackfin/
@@ -2159,7 +2161,7 @@
 
 CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER
 M:	Peter Chen <Peter.Chen@freescale.com>
-T:	git://github.com/hzpeterchen/linux-usb.git
+T:	git git://github.com/hzpeterchen/linux-usb.git
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/chipidea/
@@ -2179,9 +2181,9 @@
 F:	drivers/net/ethernet/cisco/enic/
 
 CISCO VIC LOW LATENCY NIC DRIVER
-M:      Upinder Malhi <umalhi@cisco.com>
-S:      Supported
-F:      drivers/infiniband/hw/usnic
+M:	Upinder Malhi <umalhi@cisco.com>
+S:	Supported
+F:	drivers/infiniband/hw/usnic
 
 CIRRUS LOGIC EP93XX ETHERNET DRIVER
 M:	Hartley Sweeten <hsweeten@visionengravers.com>
@@ -2378,20 +2380,20 @@
 F:	drivers/cpufreq/arm_big_little_dt.c
 
 CPUIDLE DRIVER - ARM BIG LITTLE
-M:      Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
-M:      Daniel Lezcano <daniel.lezcano@linaro.org>
-L:      linux-pm@vger.kernel.org
-L:      linux-arm-kernel@lists.infradead.org
-T:      git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
-S:      Maintained
-F:      drivers/cpuidle/cpuidle-big_little.c
+M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+L:	linux-pm@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+S:	Maintained
+F:	drivers/cpuidle/cpuidle-big_little.c
 
 CPUIDLE DRIVERS
 M:	Rafael J. Wysocki <rjw@rjwysocki.net>
 M:	Daniel Lezcano <daniel.lezcano@linaro.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
-T:	git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 F:	drivers/cpuidle/*
 F:	include/linux/cpuidle.h
 
@@ -2458,9 +2460,9 @@
 F:	sound/pci/cs5535audio/
 
 CW1200 WLAN driver
-M:     Solomon Peachy <pizza@shaftnet.org>
-S:     Maintained
-F:     drivers/net/wireless/cw1200/
+M:	Solomon Peachy <pizza@shaftnet.org>
+S:	Maintained
+F:	drivers/net/wireless/cw1200/
 
 CX18 VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
@@ -2611,9 +2613,9 @@
 M:	Oliver Neukum <oliver@neukum.org>
 M:	Ali Akcaagac <aliakc@web.de>
 M:	Jamie Lenehan <lenehan@twibble.org>
-W:	http://twibble.org/dist/dc395x/
 L:	dc395x@twibble.org
-L:	http://lists.twibble.org/mailman/listinfo/dc395x/
+W:	http://twibble.org/dist/dc395x/
+W:	http://lists.twibble.org/mailman/listinfo/dc395x/
 S:	Maintained
 F:	Documentation/scsi/dc395x.txt
 F:	drivers/scsi/dc395x.*
@@ -2848,12 +2850,22 @@
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>
 L:	dri-devel@lists.freedesktop.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+T:	git git://people.freedesktop.org/~airlied/linux
 S:	Maintained
 F:	drivers/gpu/drm/
 F:	include/drm/
 F:	include/uapi/drm/
 
+RADEON DRM DRIVERS
+M:	Alex Deucher <alexander.deucher@amd.com>
+M:	Christian König <christian.koenig@amd.com>
+L:	dri-devel@lists.freedesktop.org
+T:	git git://people.freedesktop.org/~agd5f/linux
+S:	Supported
+F:	drivers/gpu/drm/radeon/
+F:	include/drm/radeon*
+F:	include/uapi/drm/radeon*
+
 INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
 M:	Daniel Vetter <daniel.vetter@ffwll.ch>
 M:	Jani Nikula <jani.nikula@linux.intel.com>
@@ -3085,6 +3097,8 @@
 
 EDAC-CORE
 M:	Doug Thompson <dougthompson@xmission.com>
+M:	Borislav Petkov <bp@alien8.de>
+M:	Mauro Carvalho Chehab <m.chehab@samsung.com>
 L:	linux-edac@vger.kernel.org
 W:	bluesmoke.sourceforge.net
 S:	Supported
@@ -4548,6 +4562,7 @@
 F:	Documentation/networking/i40e.txt
 F:	Documentation/networking/i40evf.txt
 F:	drivers/net/ethernet/intel/
+F:	drivers/net/ethernet/intel/*/
 
 INTEL-MID GPIO DRIVER
 M:	David Cohen <david.a.cohen@linux.intel.com>
@@ -4904,7 +4919,7 @@
 KCONFIG
 M:	"Yann E. MORIN" <yann.morin.1998@free.fr>
 L:	linux-kbuild@vger.kernel.org
-T:	git://gitorious.org/linux-kconfig/linux-kconfig
+T:	git git://gitorious.org/linux-kconfig/linux-kconfig
 S:	Maintained
 F:	Documentation/kbuild/kconfig-language.txt
 F:	scripts/kconfig/
@@ -5461,11 +5476,11 @@
 F:	drivers/media/tuners/m88ts2022*
 
 MA901 MASTERKIT USB FM RADIO DRIVER
-M:      Alexey Klimov <klimov.linux@gmail.com>
-L:      linux-media@vger.kernel.org
-T:      git git://linuxtv.org/media_tree.git
-S:      Maintained
-F:      drivers/media/radio/radio-ma901.c
+M:	Alexey Klimov <klimov.linux@gmail.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/radio/radio-ma901.c
 
 MAC80211
 M:	Johannes Berg <johannes@sipsolutions.net>
@@ -5501,6 +5516,11 @@
 L:	linux-man@vger.kernel.org
 S:	Maintained
 
+MARVELL ARMADA DRM SUPPORT
+M:	Russell King <rmk+kernel@arm.linux.org.uk>
+S:	Maintained
+F:	drivers/gpu/drm/armada/
+
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
 M:	Mirko Lindner <mlindner@marvell.com>
 M:	Stephen Hemminger <stephen@networkplumber.org>
@@ -5621,7 +5641,7 @@
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
 M:	Amir Vadai <amirv@mellanox.com>
-L: 	netdev@vger.kernel.org
+L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
@@ -5662,7 +5682,7 @@
 F:	include/uapi/mtd/
 
 MEN A21 WATCHDOG DRIVER
-M:  	Johannes Thumshirn <johannes.thumshirn@men.de>
+M:	Johannes Thumshirn <johannes.thumshirn@men.de>
 L:	linux-watchdog@vger.kernel.org
 S:	Supported
 F:	drivers/watchdog/mena21_wdt.c
@@ -5718,20 +5738,20 @@
 W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
-T:	git://openfabrics.org/~eli/connect-ib.git
+T:	git git://openfabrics.org/~eli/connect-ib.git
 S:	Supported
 F:	drivers/net/ethernet/mellanox/mlx5/core/
 F:	include/linux/mlx5/
 
 Mellanox MLX5 IB driver
-M:      Eli Cohen <eli@mellanox.com>
-L:      linux-rdma@vger.kernel.org
-W:      http://www.mellanox.com
-Q:      http://patchwork.kernel.org/project/linux-rdma/list/
-T:      git://openfabrics.org/~eli/connect-ib.git
-S:      Supported
-F:      include/linux/mlx5/
-F:      drivers/infiniband/hw/mlx5/
+M:	Eli Cohen <eli@mellanox.com>
+L:	linux-rdma@vger.kernel.org
+W:	http://www.mellanox.com
+Q:	http://patchwork.kernel.org/project/linux-rdma/list/
+T:	git git://openfabrics.org/~eli/connect-ib.git
+S:	Supported
+F:	include/linux/mlx5/
+F:	drivers/infiniband/hw/mlx5/
 
 MODULE SUPPORT
 M:	Rusty Russell <rusty@rustcorp.com.au>
@@ -5983,6 +6003,8 @@
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
+F:	tools/net/
+F:	tools/testing/selftests/net/
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
@@ -6156,6 +6178,12 @@
 F:	drivers/block/nvme*
 F:	include/linux/nvme.h
 
+NXP TDA998X DRM DRIVER
+M:	Russell King <rmk+kernel@arm.linux.org.uk>
+S:	Supported
+F:	drivers/gpu/drm/i2c/tda998x_drv.c
+F:	include/drm/i2c/tda998x.h
+
 OMAP SUPPORT
 M:	Tony Lindgren <tony@atomide.com>
 L:	linux-omap@vger.kernel.org
@@ -8443,8 +8471,8 @@
 M:	Nicholas A. Bellinger <nab@linux-iscsi.org>
 L:	linux-scsi@vger.kernel.org
 L:	target-devel@vger.kernel.org
-L:	http://groups.google.com/group/linux-iscsi-target-dev
 W:	http://www.linux-iscsi.org
+W:	http://groups.google.com/group/linux-iscsi-target-dev
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master
 S:	Supported
 F:	drivers/target/
@@ -8685,17 +8713,17 @@
 F:	drivers/media/radio/radio-raremono.c
 
 THERMAL
-M:      Zhang Rui <rui.zhang@intel.com>
-M:      Eduardo Valentin <eduardo.valentin@ti.com>
-L:      linux-pm@vger.kernel.org
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
-Q:      https://patchwork.kernel.org/project/linux-pm/list/
-S:      Supported
-F:      drivers/thermal/
-F:      include/linux/thermal.h
-F:      include/linux/cpu_cooling.h
-F:      Documentation/devicetree/bindings/thermal/
+M:	Zhang Rui <rui.zhang@intel.com>
+M:	Eduardo Valentin <eduardo.valentin@ti.com>
+L:	linux-pm@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
+Q:	https://patchwork.kernel.org/project/linux-pm/list/
+S:	Supported
+F:	drivers/thermal/
+F:	include/linux/thermal.h
+F:	include/linux/cpu_cooling.h
+F:	Documentation/devicetree/bindings/thermal/
 
 THINGM BLINK(1) USB RGB LED DRIVER
 M:	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
@@ -9797,7 +9825,7 @@
 L:	mjpeg-users@lists.sourceforge.net
 L:	linux-media@vger.kernel.org
 W:	http://mjpeg.sourceforge.net/driver-zoran/
-T:	Mercurial http://linuxtv.org/hg/v4l-dvb
+T:	hg http://linuxtv.org/hg/v4l-dvb
 S:	Odd Fixes
 F:	drivers/media/pci/zoran/
 
diff --git a/Makefile b/Makefile
index 831b36a..ef779ec 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc7
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
@@ -605,10 +605,11 @@
 ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
   stackp-flag := -fstack-protector
   ifeq ($(call cc-option, $(stackp-flag)),)
-    $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \
-	      -fstack-protector not supported by compiler))
+    $(warning Cannot use CONFIG_CC_STACKPROTECTOR_REGULAR: \
+             -fstack-protector not supported by compiler)
   endif
-else ifdef CONFIG_CC_STACKPROTECTOR_STRONG
+else
+ifdef CONFIG_CC_STACKPROTECTOR_STRONG
   stackp-flag := -fstack-protector-strong
   ifeq ($(call cc-option, $(stackp-flag)),)
     $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \
@@ -618,6 +619,7 @@
   # Force off for distro compilers that enable stack protector by default.
   stackp-flag := $(call cc-option, -fno-stack-protector)
 endif
+endif
 KBUILD_CFLAGS += $(stackp-flag)
 
 # This warning generated too much noise in a regular build.
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 6b58c1d..400c663 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -282,7 +282,7 @@
 #else
 	/* if V-P const for loop, PTAG can be written once outside loop */
 	if (full_page_op)
-		write_aux_reg(ARC_REG_DC_PTAG, paddr);
+		write_aux_reg(aux_tag, paddr);
 #endif
 
 	while (num_lines-- > 0) {
@@ -296,7 +296,7 @@
 		write_aux_reg(aux_cmd, vaddr);
 		vaddr += L1_CACHE_BYTES;
 #else
-		write_aux_reg(aux, paddr);
+		write_aux_reg(aux_cmd, paddr);
 		paddr += L1_CACHE_BYTES;
 #endif
 	}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e254198..1594945 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1578,6 +1578,7 @@
 
 choice
 	prompt "Memory split"
+	depends on MMU
 	default VMSPLIT_3G
 	help
 	  Select the desired split between kernel and user memory.
@@ -1595,6 +1596,7 @@
 
 config PAGE_OFFSET
 	hex
+	default PHYS_OFFSET if !MMU
 	default 0x40000000 if VMSPLIT_1G
 	default 0x80000000 if VMSPLIT_2G
 	default 0xC0000000
@@ -1903,6 +1905,7 @@
 	depends on ARM && AEABI && OF
 	depends on CPU_V7 && !CPU_V6
 	depends on !GENERIC_ATOMIC64
+	depends on MMU
 	select ARM_PSCI
 	select SWIOTLB_XEN
 	select ARCH_DMA_ADDR_T_64BIT
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index 47279aa..0714e03 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 ashldi3.S
+bswapsdi2.S
 font.c
 lib1funcs.S
 hyp-stub.S
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index e491b82..792fde1 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -147,7 +147,7 @@
 	};
 
 	pinctrl@35004800 {
-		compatible = "brcm,capri-pinctrl";
+		compatible = "brcm,bcm11351-pinctrl";
 		reg = <0x35004800 0x430>;
 	};
 
diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi
index 2363593..ef58d1c 100644
--- a/arch/arm/boot/dts/keystone-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-clocks.dtsi
@@ -612,7 +612,7 @@
 		compatible = "ti,keystone,psc-clock";
 		clocks = <&chipclk13>;
 		clock-output-names = "vcp-3";
-		reg = <0x0235000a8 0xb00>, <0x02350060 0x400>;
+		reg = <0x023500a8 0xb00>, <0x02350060 0x400>;
 		reg-names = "control", "domain";
 		domain-id = <24>;
 	};
diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts
index c551e4a..d3b253b 100644
--- a/arch/arm/boot/dts/omap3-gta04.dts
+++ b/arch/arm/boot/dts/omap3-gta04.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "OMAP3 GTA04";
-	compatible = "ti,omap3-gta04", "ti,omap3";
+	compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 25a2b5f..f2779ac 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "IGEPv2 (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0020", "ti,omap3";
+	compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3";
 
 	leds {
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts
index 145c58c..2793749 100644
--- a/arch/arm/boot/dts/omap3-igep0030.dts
+++ b/arch/arm/boot/dts/omap3-igep0030.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "IGEP COM MODULE (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0030", "ti,omap3";
+	compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3";
 
 	leds {
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 10666ca..d4d2763 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -426,7 +426,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 6496159..79fd412 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -383,7 +383,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 320335a..c463fd730 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -346,7 +346,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <29>;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 9ff0948..6f25cf5 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -454,7 +454,7 @@
 		rtc: rtc@01c20d00 {
 			compatible = "allwinner,sun7i-a20-rtc";
 			reg = <0x01c20d00 0x20>;
-			interrupts = <0 24 1>;
+			interrupts = <0 24 4>;
 		};
 
 		sid: eeprom@01c23800 {
@@ -463,7 +463,7 @@
 		};
 
 		rtp: rtp@01c25000 {
-			compatible = "allwinner,sun4i-ts";
+			compatible = "allwinner,sun4i-a10-ts";
 			reg = <0x01c25000 0x100>;
 			interrupts = <0 29 4>;
 		};
@@ -596,10 +596,10 @@
 		hstimer@01c60000 {
 			compatible = "allwinner,sun7i-a20-hstimer";
 			reg = <0x01c60000 0x1000>;
-			interrupts = <0 81 1>,
-				     <0 82 1>,
-				     <0 83 1>,
-				     <0 84 1>;
+			interrupts = <0 81 4>,
+				     <0 82 4>,
+				     <0 83 4>,
+				     <0 84 4>;
 			clocks = <&ahb_gates 28>;
 		};
 
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 00fe9e9..27d69b5 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -204,7 +204,10 @@
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_ONESHOT=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 8756e4b..4afb376 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -30,14 +30,15 @@
  */
 #define UL(x) _AC(x, UL)
 
+/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
+
 #ifdef CONFIG_MMU
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
-#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
 #define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
@@ -104,10 +105,6 @@
 #define END_MEM     		(UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
-#ifndef PAGE_OFFSET
-#define PAGE_OFFSET		PLAT_PHYS_OFFSET
-#endif
-
 /*
  * The module can be at any place in ram in nommu mode.
  */
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 47cd974..c96ecac 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -177,6 +177,18 @@
 	.long	__proc_info_end
 	.size	__lookup_processor_type_data, . - __lookup_processor_type_data
 
+__error_lpae:
+#ifdef CONFIG_DEBUG_LL
+	adr	r0, str_lpae
+	bl 	printascii
+	b	__error
+str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
+#else
+	b	__error
+#endif
+	.align
+ENDPROC(__error_lpae)
+
 __error_p:
 #ifdef CONFIG_DEBUG_LL
 	adr	r0, str_p1
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 914616e..f5f381d 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -102,7 +102,7 @@
 	and	r3, r3, #0xf			@ extract VMSA support
 	cmp	r3, #5				@ long-descriptor translation table format?
  THUMB( it	lo )				@ force fixup-able long branch encoding
-	blo	__error_p			@ only classic page table format
+	blo	__error_lpae			@ only classic page table format
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248e..bd18bb8 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@
 				    unsigned long cmd,
 				    void *v)
 {
-	if (cmd == CPU_PM_EXIT) {
+	if (cmd == CPU_PM_EXIT &&
+	    __hyp_get_vectors() == hyp_default_vectors) {
 		cpu_init_hyp_mode(NULL);
 		return NOTIFY_OK;
 	}
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc1553..0d68d40 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@
 host_switch_to_hyp:
 	pop	{r0, r1, r2}
 
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
 	push	{lr}
 	mrs	lr, SPSR
 	push	{lr}
@@ -378,7 +387,7 @@
 	pop	{lr}
 	msr	SPSR_csxf, lr
 	pop	{lr}
-	eret
+1:	eret
 
 guest_trap:
 	load_vcpu			@ Load VCPU pointer to r0
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 3b05aea..11ed915 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -433,7 +433,9 @@
 	.enable		= &omap2_dflt_clk_enable,
 	.disable	= &omap2_dflt_clk_disable,
 	.is_enabled	= &omap2_dflt_clk_is_enabled,
+	.set_rate	= &omap3_clkoutx2_set_rate,
 	.recalc_rate	= &omap3_clkoutx2_recalc,
+	.round_rate	= &omap3_clkoutx2_round_rate,
 };
 
 static const struct clk_ops dpll4_m5x2_ck_3630_ops = {
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 4c158c8..01fc710 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -23,6 +23,8 @@
 #include "prm.h"
 #include "clockdomain.h"
 
+#define MAX_CPUS	2
+
 /* Machine specific information */
 struct idle_statedata {
 	u32 cpu_state;
@@ -48,11 +50,11 @@
 	},
 };
 
-static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS];
-static struct clockdomain *cpu_clkdm[NR_CPUS];
+static struct powerdomain *mpu_pd, *cpu_pd[MAX_CPUS];
+static struct clockdomain *cpu_clkdm[MAX_CPUS];
 
 static atomic_t abort_barrier;
-static bool cpu_done[NR_CPUS];
+static bool cpu_done[MAX_CPUS];
 static struct idle_statedata *state_ptr = &omap4_idle_data[0];
 
 /* Private functions */
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index 3185ced..3c418ea 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -623,25 +623,12 @@
 
 /* Clock control for DPLL outputs */
 
-/**
- * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
- * @clk: DPLL output struct clk
- *
- * Using parent clock DPLL data, look up DPLL state.  If locked, set our
- * rate to the dpll_clk * 2; otherwise, just use dpll_clk.
- */
-unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
-				    unsigned long parent_rate)
+/* Find the parent DPLL for the given clkoutx2 clock */
+static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw)
 {
-	const struct dpll_data *dd;
-	unsigned long rate;
-	u32 v;
 	struct clk_hw_omap *pclk = NULL;
 	struct clk *parent;
 
-	if (!parent_rate)
-		return 0;
-
 	/* Walk up the parents of clk, looking for a DPLL */
 	do {
 		do {
@@ -656,9 +643,35 @@
 	/* clk does not have a DPLL as a parent?  error in the clock data */
 	if (!pclk) {
 		WARN_ON(1);
-		return 0;
+		return NULL;
 	}
 
+	return pclk;
+}
+
+/**
+ * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
+ * @clk: DPLL output struct clk
+ *
+ * Using parent clock DPLL data, look up DPLL state.  If locked, set our
+ * rate to the dpll_clk * 2; otherwise, just use dpll_clk.
+ */
+unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
+				    unsigned long parent_rate)
+{
+	const struct dpll_data *dd;
+	unsigned long rate;
+	u32 v;
+	struct clk_hw_omap *pclk = NULL;
+
+	if (!parent_rate)
+		return 0;
+
+	pclk = omap3_find_clkoutx2_dpll(hw);
+
+	if (!pclk)
+		return 0;
+
 	dd = pclk->dpll_data;
 
 	WARN_ON(!dd->enable_mask);
@@ -672,6 +685,55 @@
 	return rate;
 }
 
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate)
+{
+	return 0;
+}
+
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *prate)
+{
+	const struct dpll_data *dd;
+	u32 v;
+	struct clk_hw_omap *pclk = NULL;
+
+	if (!*prate)
+		return 0;
+
+	pclk = omap3_find_clkoutx2_dpll(hw);
+
+	if (!pclk)
+		return 0;
+
+	dd = pclk->dpll_data;
+
+	/* TYPE J does not have a clkoutx2 */
+	if (dd->flags & DPLL_J_TYPE) {
+		*prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate);
+		return *prate;
+	}
+
+	WARN_ON(!dd->enable_mask);
+
+	v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
+	v >>= __ffs(dd->enable_mask);
+
+	/* If in bypass, the rate is fixed to the bypass rate*/
+	if (v != OMAP3XXX_EN_DPLL_LOCKED)
+		return *prate;
+
+	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+		unsigned long best_parent;
+
+		best_parent = (rate / 2);
+		*prate = __clk_round_rate(__clk_get_parent(hw->clk),
+				best_parent);
+	}
+
+	return *prate * 2;
+}
+
 /* OMAP3/4 non-CORE DPLL clkops */
 const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
 	.allow_idle	= omap3_dpll_allow_idle,
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 42d8188..1f33f5d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1947,29 +1947,31 @@
 		goto dis_opt_clks;
 
 	_write_sysconfig(v, oh);
+
+	if (oh->class->sysc->srst_udelay)
+		udelay(oh->class->sysc->srst_udelay);
+
+	c = _wait_softreset_complete(oh);
+	if (c == MAX_MODULE_SOFTRESET_WAIT) {
+		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
+			   oh->name, MAX_MODULE_SOFTRESET_WAIT);
+		ret = -ETIMEDOUT;
+		goto dis_opt_clks;
+	} else {
+		pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
+	}
+
 	ret = _clear_softreset(oh, &v);
 	if (ret)
 		goto dis_opt_clks;
 
 	_write_sysconfig(v, oh);
 
-	if (oh->class->sysc->srst_udelay)
-		udelay(oh->class->sysc->srst_udelay);
-
-	c = _wait_softreset_complete(oh);
-	if (c == MAX_MODULE_SOFTRESET_WAIT)
-		pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
-			   oh->name, MAX_MODULE_SOFTRESET_WAIT);
-	else
-		pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
-
 	/*
 	 * XXX add _HWMOD_STATE_WEDGED for modules that don't come back from
 	 * _wait_target_ready() or _reset()
 	 */
 
-	ret = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
-
 dis_opt_clks:
 	if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
 		_disable_optional_clocks(oh);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 18f333c..810c205 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1365,11 +1365,10 @@
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
 	.syss_offs	= 0x0014,
-	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
-			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
-			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 3d5b24d..c33e07e 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -22,6 +22,8 @@
 #include "common-board-devices.h"
 #include "dss-common.h"
 #include "control.h"
+#include "omap-secure.h"
+#include "soc.h"
 
 struct pdata_init {
 	const char *compatible;
@@ -169,6 +171,22 @@
 	omap_ctrl_writel(v, AM35XX_CONTROL_IP_SW_RESET);
 	omap_ctrl_readl(AM35XX_CONTROL_IP_SW_RESET); /* OCP barrier */
 }
+
+static void __init nokia_n900_legacy_init(void)
+{
+	hsmmc2_internal_input_clk();
+
+	if (omap_type() == OMAP2_DEVICE_TYPE_SEC) {
+		if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) {
+			pr_info("RX-51: Enabling ARM errata 430973 workaround\n");
+			/* set IBE to 1 */
+			rx51_secure_update_aux_cr(BIT(6), 0);
+		} else {
+			pr_warning("RX-51: Not enabling ARM errata 430973 workaround\n");
+			pr_warning("Thumb binaries may crash randomly without this workaround\n");
+		}
+	}
+}
 #endif /* CONFIG_ARCH_OMAP3 */
 
 #ifdef CONFIG_ARCH_OMAP4
@@ -239,6 +257,7 @@
 #endif
 #ifdef CONFIG_ARCH_OMAP3
 	OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002030, "48002030.pinmux", &pcs_pdata),
+	OF_DEV_AUXDATA("ti,omap3-padconf", 0x480025a0, "480025a0.pinmux", &pcs_pdata),
 	OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002a00, "48002a00.pinmux", &pcs_pdata),
 	/* Only on am3517 */
 	OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
@@ -259,7 +278,7 @@
 static struct pdata_init pdata_quirks[] __initdata = {
 #ifdef CONFIG_ARCH_OMAP3
 	{ "compulab,omap3-sbc-t3730", omap3_sbc_t3730_legacy_init, },
-	{ "nokia,omap3-n900", hsmmc2_internal_input_clk, },
+	{ "nokia,omap3-n900", nokia_n900_legacy_init, },
 	{ "nokia,omap3-n9", hsmmc2_internal_input_clk, },
 	{ "nokia,omap3-n950", hsmmc2_internal_input_clk, },
 	{ "isee,omap3-igep0020", omap3_igep0020_legacy_init, },
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index 6334b96..280f3c5 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -183,11 +183,11 @@
 					OMAP4_PRM_RSTCTRL_OFFSET);
 	v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK;
 	omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION,
-				 OMAP4430_PRM_DEVICE_INST,
+				 dev_inst,
 				 OMAP4_PRM_RSTCTRL_OFFSET);
 
 	/* OCP barrier */
 	v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION,
-				    OMAP4430_PRM_DEVICE_INST,
+				    dev_inst,
 				    OMAP4_PRM_RSTCTRL_OFFSET);
 }
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d..50e1d85 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
 
+#include "hardware.h" /* Gives GPIO_MAX */
+
 extern void locomolcd_power(int on);
 
 #define COLLIE_SCOOP_GPIO_BASE	(GPIO_MAX + 1)
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 2b3a564..ef69152 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -264,6 +264,9 @@
 			note_page(st, addr, 3, pmd_val(*pmd));
 		else
 			walk_pte(st, pmd, addr);
+
+		if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1]))
+			note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1]));
 	}
 }
 
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 13fb0b3..453a179 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#ifdef CONFIG_SMP
+
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -36,6 +38,12 @@
 }
 #define __my_cpu_offset __my_cpu_offset()
 
+#else	/* !CONFIG_SMP */
+
+#define set_my_cpu_offset(x)	do { } while (0)
+
+#endif /* CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b524dcd..aa3917c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -136,11 +136,11 @@
 /*
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
-#define pte_present(pte)	(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))
-#define pte_dirty(pte)		(pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & PTE_AF)
-#define pte_special(pte)	(pte_val(pte) & PTE_SPECIAL)
-#define pte_write(pte)		(pte_val(pte) & PTE_WRITE)
+#define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_dirty(pte)		(!!(pte_val(pte) & PTE_DIRTY))
+#define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #define pte_valid_user(pte) \
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index c3b6c63..38f0558 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,7 +48,11 @@
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	/*
+	 * -4 here because we care about the PC at time of bl,
+	 * not where the return will go.
+	 */
+	frame->pc = *(unsigned long *)(fp + 8) - 4;
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36..2c56012 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@
 
 	.align	2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	ret
@@ -737,7 +755,12 @@
 	pop	x2, x3
 	pop	x0, x1
 
-	push	lr, xzr
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@
 	blr	lr
 
 	pop	lr, xzr
-	eret
+2:	eret
 
 el1_trap:
 	/*
diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h
index 09c5a0f..86648c0 100644
--- a/arch/c6x/include/asm/cache.h
+++ b/arch/c6x/include/asm/cache.h
@@ -12,6 +12,7 @@
 #define _ASM_C6X_CACHE_H
 
 #include <linux/irqflags.h>
+#include <linux/init.h>
 
 /*
  * Cache line size
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index 184066c..053c17b 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -144,7 +144,7 @@
  * definition, which doesn't have the same semantics.  We don't want to
  * use -fno-builtin, so just hide the name ffs.
  */
-#define ffs kernel_ffs
+#define ffs(x) kernel_ffs(x)
 
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index a96bcf8..20e8a9b 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,7 @@
 	/* attempt to allocate a granule's worth of cached memory pages */
 
 	page = alloc_pages_exact_node(nid,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
 	if (!page) {
 		mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 7cc8c36..6fb9e81 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,4 @@
-
+generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cputime.h
@@ -6,6 +6,7 @@
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
@@ -18,6 +19,7 @@
 generic-y += mman.h
 generic-y += mutex.h
 generic-y += percpu.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
@@ -31,5 +33,3 @@
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
deleted file mode 100644
index 15c5f77..0000000
--- a/arch/m68k/include/asm/barrier.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _M68K_BARRIER_H
-#define _M68K_BARRIER_H
-
-#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-
-#include <asm-generic/barrier.h>
-
-#endif /* _M68K_BARRIER_H */
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 014f288..9d38b73 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		349
+#define NR_syscalls		351
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 625f321..b932dd4 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -354,5 +354,7 @@
 #define __NR_process_vm_writev	346
 #define __NR_kcmp		347
 #define __NR_finit_module	348
+#define __NR_sched_setattr	349
+#define __NR_sched_getattr	350
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 3f04ea0..b6223dc4 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -369,4 +369,6 @@
 	.long sys_process_vm_writev
 	.long sys_kcmp
 	.long sys_finit_module
+	.long sys_sched_setattr
+	.long sys_sched_getattr		/* 350 */
 
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf68..a613d2c 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -200,10 +200,11 @@
 
 	/*
 	 * We can't access below the stack pointer in the 32bit ABI and
-	 * can access 288 bytes in the 64bit ABI
+	 * can access 288 bytes in the 64bit big-endian ABI,
+	 * or 512 bytes with the new ELFv2 little-endian ABI.
 	 */
 	if (!is_32bit_task())
-		usp -= 288;
+		usp -= USER_REDZONE_SIZE;
 
 	return (void __user *) (usp - len);
 }
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..ed82142 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		       uint32_t addr, uint32_t data, uint32_t sz);
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e..279b80f 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -28,11 +28,23 @@
 
 #ifdef __powerpc64__
 
+/*
+ * Size of redzone that userspace is allowed to use below the stack
+ * pointer.  This is 288 in the 64-bit big-endian ELF ABI, and 512 in
+ * the new ELFv2 little-endian ABI, so we allow the larger amount.
+ *
+ * For kernel code we allow a 288-byte redzone, in order to conserve
+ * kernel stack space; gcc currently only uses 288 bytes, and will
+ * hopefully allow explicit control of the redzone size in future.
+ */
+#define USER_REDZONE_SIZE	512
+#define KERNEL_REDZONE_SIZE	288
+
 #define STACK_FRAME_OVERHEAD	112	/* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE	2	/* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x7265677368657265)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + \
-					STACK_FRAME_OVERHEAD + 288)
+				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
 /* Size of dummy stack frame allocated when calling signal handler. */
@@ -41,6 +53,8 @@
 
 #else /* __powerpc64__ */
 
+#define USER_REDZONE_SIZE	0
+#define KERNEL_REDZONE_SIZE	0
 #define STACK_FRAME_OVERHEAD	16	/* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE	1	/* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 11c1d06..7a13f37 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -98,17 +98,19 @@
 			size_t csize, unsigned long offset, int userbuf)
 {
 	void  *vaddr;
+	phys_addr_t paddr;
 
 	if (!csize)
 		return 0;
 
 	csize = min_t(size_t, csize, PAGE_SIZE);
+	paddr = pfn << PAGE_SHIFT;
 
-	if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
-		vaddr = __va(pfn << PAGE_SHIFT);
+	if (memblock_is_region_memory(paddr, csize)) {
+		vaddr = __va(paddr);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 	} else {
-		vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+		vaddr = __ioremap(paddr, PAGE_SIZE, 0);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 		iounmap(vaddr);
 	}
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 9b27b29..b0ded97 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -74,6 +74,7 @@
  */
 static int test_24bit_addr(unsigned long ip, unsigned long addr)
 {
+	addr = ppc_function_entry((void *)addr);
 
 	/* use the create_branch to verify that this offset can be branched */
 	return create_branch((unsigned int *)ip, addr, 0);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8d4c247f1..af064d2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1048,6 +1048,15 @@
 	flush_altivec_to_thread(src);
 	flush_vsx_to_thread(src);
 	flush_spe_to_thread(src);
+	/*
+	 * Flush TM state out so we can copy it.  __switch_to_tm() does this
+	 * flush but it removes the checkpointed state from the current CPU and
+	 * transitions the CPU out of TM mode.  Hence we need to call
+	 * tm_recheckpoint_new_task() (on the same task) to restore the
+	 * checkpointed state back and the TM mode.
+	 */
+	__switch_to_tm(src);
+	tm_recheckpoint_new_task(src);
 
 	*dst = *src;
 
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index 1482327..d88736f 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -81,6 +81,7 @@
 
 6:	blr
 
+.balign 8
 p_dyn:	.llong	__dynamic_start - 0b
 p_rela:	.llong	__rela_dyn_start - 0b
 p_st:	.llong	_stext - 0b
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e35bf77..8d253c2 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -65,8 +65,8 @@
 	struct siginfo __user *pinfo;
 	void __user *puc;
 	struct siginfo info;
-	/* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
-	char abigap[288];
+	/* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+	char abigap[USER_REDZONE_SIZE];
 } __attribute__ ((aligned (16)));
 
 static const char fmt32[] = KERN_INFO \
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 5ec1e47..e865d74 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -123,7 +123,8 @@
 
 	area->nid = nid;
 	area->order = order;
-	area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+	area->pages = alloc_pages_exact_node(area->nid,
+						GFP_KERNEL|__GFP_THISNODE,
 						area->order);
 
 	if (!area->pages) {
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index f514743..253fefe 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -114,6 +114,7 @@
 			ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
 #endif /* CONFIG_DEBUG_FS */
 
+
 /**
  * ioda_eeh_post_init - Chip dependent post initialization
  * @hose: PCI controller
@@ -221,6 +222,22 @@
 	return ret;
 }
 
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	long rc;
+
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+			    __func__, hose->global_number, rc);
+		return;
+	}
+
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
 /**
  * ioda_eeh_get_state - Retrieve the state of PE
  * @pe: EEH PE
@@ -272,6 +289,9 @@
 			result |= EEH_STATE_DMA_ACTIVE;
 			result |= EEH_STATE_MMIO_ENABLED;
 			result |= EEH_STATE_DMA_ENABLED;
+		} else if (!(pe->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+			ioda_eeh_phb_diag(hose);
 		}
 
 		return result;
@@ -315,6 +335,15 @@
 			   __func__, fstate, hose->global_number, pe_no);
 	}
 
+	/* Dump PHB diag-data for frozen PE */
+	if (result != EEH_STATE_NOT_SUPPORT &&
+	    (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+	    !(pe->state & EEH_PE_ISOLATED)) {
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		ioda_eeh_phb_diag(hose);
+	}
+
 	return result;
 }
 
@@ -530,42 +559,6 @@
 }
 
 /**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-			    char *drv_log, unsigned long len)
-{
-	s64 ret;
-	unsigned long flags;
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-
-	spin_lock_irqsave(&phb->lock, flags);
-
-	ret = opal_pci_get_phb_diag_data2(phb->opal_id,
-			phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
-	if (ret) {
-		spin_unlock_irqrestore(&phb->lock, flags);
-		pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
-			   __func__, hose->global_number, pe->addr, ret);
-		return -EIO;
-	}
-
-	/* The PHB diag-data is always indicative */
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
-	spin_unlock_irqrestore(&phb->lock, flags);
-
-	return 0;
-}
-
-/**
  * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
  * @pe: EEH PE
  *
@@ -646,22 +639,6 @@
 	}
 }
 
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
-	struct pnv_phb *phb = hose->private_data;
-	long rc;
-
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
-					 PNV_PCI_DIAG_BUF_SIZE);
-	if (rc != OPAL_SUCCESS) {
-		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
-			    __func__, hose->global_number, rc);
-		return;
-	}
-
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
 static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
 			       struct eeh_pe **pe)
 {
@@ -835,6 +812,20 @@
 		}
 
 		/*
+		 * EEH core will try recover from fenced PHB or
+		 * frozen PE. In the time for frozen PE, EEH core
+		 * enable IO path for that before collecting logs,
+		 * but it ruins the site. So we have to dump the
+		 * log in advance here.
+		 */
+		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
+		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
+		    !((*pe)->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+			ioda_eeh_phb_diag(hose);
+		}
+
+		/*
 		 * If we have no errors on the specific PHB or only
 		 * informative error there, we continue poking it.
 		 * Otherwise, we need actions to be taken by upper
@@ -852,7 +843,6 @@
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
-	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276..4cd2ea6 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@
 	}
 }
 
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
 {
 	/*
 	 * XSCOM indirect addresses have the top bit set. Additionally
-	 * the reset of the top 3 nibbles is always 0.
+	 * the rest of the top 3 nibbles is always 0.
 	 *
 	 * Because the debugfs interface uses signed offsets and shifts
 	 * the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@
 	 * conversion here. To leave room for further xscom address
 	 * expansion, we only clear out the top byte
 	 *
+	 * For in-kernel use, we also support the real indirect bit, so
+	 * we test for any of the top 5 bits
+	 *
 	 */
-	if (reg & (1ull << 59))
-		reg = (reg & ~(0xffull << 56)) | (1ull << 63);
-	return reg;
+	if (addr & (0x1full << 59))
+		addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+	return addr;
 }
 
 static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@
 	int64_t rc;
 	__be64 v;
 
-	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+	reg = opal_scom_unmangle(m->addr + reg);
+	rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
 	*value = be64_to_cpu(v);
 	return opal_xscom_err_xlate(rc);
 }
@@ -109,8 +112,8 @@
 	struct opal_scom_map *m = map;
 	int64_t rc;
 
-	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_write(m->chip, m->addr + reg, value);
+	reg = opal_scom_unmangle(m->addr + reg);
+	rc = opal_xscom_write(m->chip, reg, value);
 	return opal_xscom_err_xlate(rc);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 95633d7..8518817 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@
 	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
 		hose->global_number, common->version);
 
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+	if (data->brdgCtl)
+		pr_info("  brdgCtl:     %08x\n",
+			data->brdgCtl);
+	if (data->portStatusReg || data->rootCmplxStatus ||
+	    data->busAgentStatus)
+		pr_info("  UtlSts:      %08x %08x %08x\n",
+			data->portStatusReg, data->rootCmplxStatus,
+			data->busAgentStatus);
+	if (data->deviceStatus || data->slotStatus   ||
+	    data->linkStatus   || data->devCmdStatus ||
+	    data->devSecStatus)
+		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+			data->deviceStatus, data->slotStatus,
+			data->linkStatus, data->devCmdStatus,
+			data->devSecStatus);
+	if (data->rootErrorStatus   || data->uncorrErrorStatus ||
+	    data->corrErrorStatus)
+		pr_info("  RootErrSts:  %08x %08x %08x\n",
+			data->rootErrorStatus, data->uncorrErrorStatus,
+			data->corrErrorStatus);
+	if (data->tlpHdr1 || data->tlpHdr2 ||
+	    data->tlpHdr3 || data->tlpHdr4)
+		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+			data->tlpHdr1, data->tlpHdr2,
+			data->tlpHdr3, data->tlpHdr4);
+	if (data->sourceId || data->errorClass ||
+	    data->correlator)
+		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+			data->sourceId, data->errorClass,
+			data->correlator);
+	if (data->p7iocPlssr || data->p7iocCsr)
+		pr_info("  PhbSts:      %016llx %016llx\n",
+			data->p7iocPlssr, data->p7iocCsr);
+	if (data->lemFir || data->lemErrorMask ||
+	    data->lemWOF)
+		pr_info("  Lem:         %016llx %016llx %016llx\n",
+			data->lemFir, data->lemErrorMask,
+			data->lemWOF);
+	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+	    data->phbErrorLog0   || data->phbErrorLog1)
+		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+			data->phbErrorStatus, data->phbFirstErrorStatus,
+			data->phbErrorLog0, data->phbErrorLog1);
+	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+	    data->mmioErrorLog0   || data->mmioErrorLog1)
+		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+			data->mmioErrorStatus, data->mmioFirstErrorStatus,
+			data->mmioErrorLog0, data->mmioErrorLog1);
+	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
+		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+			data->dma0ErrorLog0, data->dma0ErrorLog1);
+	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
+		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+			i, data->pestA[i], data->pestB[i]);
 	}
 }
 
@@ -197,62 +212,77 @@
 	data = (struct OpalIoPhb3ErrorData*)common;
 	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
 		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-
-	pr_info("  nFir:                 %016llx\n", data->nFir);
-	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
-	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
-	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
-	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+	if (data->brdgCtl)
+		pr_info("  brdgCtl:     %08x\n",
+			data->brdgCtl);
+	if (data->portStatusReg || data->rootCmplxStatus ||
+	    data->busAgentStatus)
+		pr_info("  UtlSts:      %08x %08x %08x\n",
+			data->portStatusReg, data->rootCmplxStatus,
+			data->busAgentStatus);
+	if (data->deviceStatus || data->slotStatus   ||
+	    data->linkStatus   || data->devCmdStatus ||
+	    data->devSecStatus)
+		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+			data->deviceStatus, data->slotStatus,
+			data->linkStatus, data->devCmdStatus,
+			data->devSecStatus);
+	if (data->rootErrorStatus || data->uncorrErrorStatus ||
+	    data->corrErrorStatus)
+		pr_info("  RootErrSts:  %08x %08x %08x\n",
+			data->rootErrorStatus, data->uncorrErrorStatus,
+			data->corrErrorStatus);
+	if (data->tlpHdr1 || data->tlpHdr2 ||
+	    data->tlpHdr3 || data->tlpHdr4)
+		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+			data->tlpHdr1, data->tlpHdr2,
+			data->tlpHdr3, data->tlpHdr4);
+	if (data->sourceId || data->errorClass ||
+	    data->correlator)
+		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+			data->sourceId, data->errorClass,
+			data->correlator);
+	if (data->nFir || data->nFirMask ||
+	    data->nFirWOF)
+		pr_info("  nFir:        %016llx %016llx %016llx\n",
+			data->nFir, data->nFirMask,
+			data->nFirWOF);
+	if (data->phbPlssr || data->phbCsr)
+		pr_info("  PhbSts:      %016llx %016llx\n",
+			data->phbPlssr, data->phbCsr);
+	if (data->lemFir || data->lemErrorMask ||
+	    data->lemWOF)
+		pr_info("  Lem:         %016llx %016llx %016llx\n",
+			data->lemFir, data->lemErrorMask,
+			data->lemWOF);
+	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+	    data->phbErrorLog0   || data->phbErrorLog1)
+		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+			data->phbErrorStatus, data->phbFirstErrorStatus,
+			data->phbErrorLog0, data->phbErrorLog1);
+	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+	    data->mmioErrorLog0   || data->mmioErrorLog1)
+		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+			data->mmioErrorStatus, data->mmioFirstErrorStatus,
+			data->mmioErrorLog0, data->mmioErrorLog1);
+	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
+		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+			data->dma0ErrorLog0, data->dma0ErrorLog1);
+	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
+		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+			i, data->pestA[i], data->pestB[i]);
 	}
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 82789e7..0ea99e3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,12 +35,7 @@
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
-	.token = RTAS_UNKNOWN_SERVICE,
-	.nargs = 0,
-	.nret = 1,
-	.rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
 
 static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
 							CPU_STATE_OFFLINE;
@@ -93,15 +88,20 @@
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args *args = &rtas_stop_self_args;
+	struct rtas_args args = {
+		.token = cpu_to_be32(rtas_stop_self_token),
+		.nargs = 0,
+		.nret = 1,
+		.rets = &args.args[0],
+	};
 
 	local_irq_disable();
 
-	BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
 
 	printk("cpu %u (hwid %u) Ready to die...\n",
 	       smp_processor_id(), hard_smp_processor_id());
-	enter_rtas(__pa(args));
+	enter_rtas(__pa(&args));
 
 	panic("Alas, I survived.\n");
 }
@@ -392,10 +392,10 @@
 		}
 	}
 
-	rtas_stop_self_args.token = rtas_token("stop-self");
+	rtas_stop_self_token = rtas_token("stop-self");
 	qcss_tok = rtas_token("query-cpu-stopped-state");
 
-	if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+	if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
 			qcss_tok == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "CPU Hotplug not supported by firmware "
 				"- disabling.\n");
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 59c8efc..0248949 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1421,5 +1421,5 @@
 ENTRY(sys_sched_getattr_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgtr	%r3,%r3			# const char __user *
-	llgfr	%r3,%r3			# unsigned int
+	llgfr	%r4,%r4			# unsigned int
 	jg	sys_sched_getattr
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 60c11a6..f91c031 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -206,11 +206,13 @@
 	zdev->dma_table = NULL;
 }
 
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
-				   int size)
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+				       unsigned long start, int size)
 {
-	unsigned long boundary_size = 0x1000000;
+	unsigned long boundary_size;
 
+	boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, 0, boundary_size, 0);
 }
diff --git a/arch/sh/include/cpu-sh2/cpu/cache.h b/arch/sh/include/cpu-sh2/cpu/cache.h
index 673515b..aa1b2b9 100644
--- a/arch/sh/include/cpu-sh2/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2/cpu/cache.h
@@ -18,7 +18,7 @@
 #define SH_CACHE_ASSOC		8
 
 #if defined(CONFIG_CPU_SUBTYPE_SH7619)
-#define CCR		0xffffffec
+#define SH_CCR		0xffffffec
 
 #define CCR_CACHE_CE	0x01	/* Cache enable */
 #define CCR_CACHE_WT	0x02    /* CCR[bit1=1,bit2=1] */
diff --git a/arch/sh/include/cpu-sh2a/cpu/cache.h b/arch/sh/include/cpu-sh2a/cpu/cache.h
index defb0ba..b27ce92 100644
--- a/arch/sh/include/cpu-sh2a/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2a/cpu/cache.h
@@ -17,8 +17,8 @@
 #define SH_CACHE_COMBINED	4
 #define SH_CACHE_ASSOC		8
 
-#define CCR		0xfffc1000 /* CCR1 */
-#define CCR2		0xfffc1004
+#define SH_CCR		0xfffc1000 /* CCR1 */
+#define SH_CCR2		0xfffc1004
 
 /*
  * Most of the SH-2A CCR1 definitions resemble the SH-4 ones. All others not
diff --git a/arch/sh/include/cpu-sh3/cpu/cache.h b/arch/sh/include/cpu-sh3/cpu/cache.h
index bee2d81..29700fd 100644
--- a/arch/sh/include/cpu-sh3/cpu/cache.h
+++ b/arch/sh/include/cpu-sh3/cpu/cache.h
@@ -17,7 +17,7 @@
 #define SH_CACHE_COMBINED	4
 #define SH_CACHE_ASSOC		8
 
-#define CCR		0xffffffec	/* Address of Cache Control Register */
+#define SH_CCR		0xffffffec	/* Address of Cache Control Register */
 
 #define CCR_CACHE_CE	0x01	/* Cache Enable */
 #define CCR_CACHE_WT	0x02	/* Write-Through (for P0,U0,P3) (else writeback) */
diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h
index 7bfb9e8..92c4cd1 100644
--- a/arch/sh/include/cpu-sh4/cpu/cache.h
+++ b/arch/sh/include/cpu-sh4/cpu/cache.h
@@ -17,7 +17,7 @@
 #define SH_CACHE_COMBINED	4
 #define SH_CACHE_ASSOC		8
 
-#define CCR		0xff00001c	/* Address of Cache Control Register */
+#define SH_CCR		0xff00001c	/* Address of Cache Control Register */
 #define CCR_CACHE_OCE	0x0001	/* Operand Cache Enable */
 #define CCR_CACHE_WT	0x0002	/* Write-Through (for P0,U0,P3) (else writeback)*/
 #define CCR_CACHE_CB	0x0004	/* Copy-Back (for P1) (else writethrough) */
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index ecf83cd..0d7360d 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -112,7 +112,7 @@
 	unsigned long ccr, flags;
 
 	jump_to_uncached();
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 
 	/*
 	 * At this point we don't know whether the cache is enabled or not - a
@@ -189,7 +189,7 @@
 
 	l2_cache_init();
 
-	__raw_writel(flags, CCR);
+	__raw_writel(flags, SH_CCR);
 	back_to_cached();
 }
 #else
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 1157251..777e50f 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -36,7 +36,7 @@
 	 */
 	jump_to_uncached();
 
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 	if ((ccr & CCR_CACHE_ENABLE) == 0) {
 		back_to_cached();
 
diff --git a/arch/sh/mm/cache-sh2.c b/arch/sh/mm/cache-sh2.c
index defcf71..a74259f 100644
--- a/arch/sh/mm/cache-sh2.c
+++ b/arch/sh/mm/cache-sh2.c
@@ -63,9 +63,9 @@
 	local_irq_save(flags);
 	jump_to_uncached();
 
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 	ccr |= CCR_CACHE_INVALIDATE;
-	__raw_writel(ccr, CCR);
+	__raw_writel(ccr, SH_CCR);
 
 	back_to_cached();
 	local_irq_restore(flags);
diff --git a/arch/sh/mm/cache-sh2a.c b/arch/sh/mm/cache-sh2a.c
index 949e2d3..ee87d08 100644
--- a/arch/sh/mm/cache-sh2a.c
+++ b/arch/sh/mm/cache-sh2a.c
@@ -134,7 +134,8 @@
 
 	/* If there are too many pages then just blow the cache */
 	if (((end - begin) >> PAGE_SHIFT) >= MAX_OCACHE_PAGES) {
-		__raw_writel(__raw_readl(CCR) | CCR_OCACHE_INVALIDATE, CCR);
+		__raw_writel(__raw_readl(SH_CCR) | CCR_OCACHE_INVALIDATE,
+			     SH_CCR);
 	} else {
 		for (v = begin; v < end; v += L1_CACHE_BYTES)
 			sh2a_invalidate_line(CACHE_OC_ADDRESS_ARRAY, v);
@@ -167,7 +168,8 @@
 	/* I-Cache invalidate */
 	/* If there are too many pages then just blow the cache */
 	if (((end - start) >> PAGE_SHIFT) >= MAX_ICACHE_PAGES) {
-		__raw_writel(__raw_readl(CCR) | CCR_ICACHE_INVALIDATE, CCR);
+		__raw_writel(__raw_readl(SH_CCR) | CCR_ICACHE_INVALIDATE,
+			     SH_CCR);
 	} else {
 		for (v = start; v < end; v += L1_CACHE_BYTES)
 			sh2a_invalidate_line(CACHE_IC_ADDRESS_ARRAY, v);
diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c
index 0e52928..51d8f7f 100644
--- a/arch/sh/mm/cache-sh4.c
+++ b/arch/sh/mm/cache-sh4.c
@@ -133,9 +133,9 @@
 	jump_to_uncached();
 
 	/* Flush I-cache */
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 	ccr |= CCR_CACHE_ICI;
-	__raw_writel(ccr, CCR);
+	__raw_writel(ccr, SH_CCR);
 
 	/*
 	 * back_to_cached() will take care of the barrier for us, don't add
diff --git a/arch/sh/mm/cache-shx3.c b/arch/sh/mm/cache-shx3.c
index c0adbee..24c58b7 100644
--- a/arch/sh/mm/cache-shx3.c
+++ b/arch/sh/mm/cache-shx3.c
@@ -19,7 +19,7 @@
 {
 	unsigned int ccr;
 
-	ccr = __raw_readl(CCR);
+	ccr = __raw_readl(SH_CCR);
 
 	/*
 	 * If we've got cache aliases, resolve them in hardware.
@@ -40,5 +40,5 @@
 	ccr |= CCR_CACHE_IBE;
 #endif
 
-	writel_uncached(ccr, CCR);
+	writel_uncached(ccr, SH_CCR);
 }
diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c
index 616966a..097c2cd 100644
--- a/arch/sh/mm/cache.c
+++ b/arch/sh/mm/cache.c
@@ -285,8 +285,8 @@
 {
 	unsigned int cache_disabled = 0;
 
-#ifdef CCR
-	cache_disabled = !(__raw_readl(CCR) & CCR_CACHE_ENABLE);
+#ifdef SH_CCR
+	cache_disabled = !(__raw_readl(SH_CCR) & CCR_CACHE_ENABLE);
 #endif
 
 	compute_alias(&boot_cpu_data.icache);
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca..f3aaf23 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@
 	def_bool y
 	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
 
-config X86_OOSTORE
-	def_bool y
-	depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
 #
 # P6_NOPs are a relatively minor optimization that require a family >=
 # 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f4..4dbf967 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@
 };
 
 #define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
 
 static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
 {
@@ -180,7 +180,7 @@
 }
 
 /* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
 {
 	int i;
 
@@ -192,8 +192,9 @@
 	return false;
 }
 
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			   CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
 
 static void slots_append(unsigned long addr)
 {
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 04a4890..69bbb48 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -85,11 +85,7 @@
 #else
 # define smp_rmb()	barrier()
 #endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
+#define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
@@ -100,7 +96,7 @@
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
 #endif /* SMP */
 
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
  * For either of these options x86 doesn't have a strong TSO memory
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3d6b9f8..acd86c8 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -134,6 +134,7 @@
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);
+extern void __init efi_apply_memmap_quirks(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34f69cb..91d9c69 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -237,7 +237,7 @@
 
 static inline void flush_write_buffers(void)
 {
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
 #endif
 }
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index bf156de..0f62f54 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -26,10 +26,9 @@
 # define LOCK_PTR_REG "D"
 #endif
 
-#if defined(CONFIG_X86_32) && \
-	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
 /*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * On PPro SMP, we use a locked operation to unlock
  * (PPro errata 66, 92)
  */
 # define UNLOCK_LOCK_PREFIX LOCK_PREFIX
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779eda..d8fba5c 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
-	u32 s = 1;
-
-	while (s <= x)
-		s <<= 1;
-
-	return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
-	u32 lo, hi;
-
-	hi = base & ~0xFFF;
-	lo = ~(size-1);		/* Size is a power of 2 so this makes a mask */
-	lo &= ~0xFFF;		/* Remove the ctrl value bits */
-	lo |= key;		/* Attribute we wish to set */
-	wrmsr(reg+MSR_IDT_MCR0, lo, hi);
-	mtrr_centaur_report_mcr(reg, lo, hi);	/* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
-	u32 clip = 0xFFFFFFFFUL;
-	u32 top = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		unsigned long start, end;
-
-		if (e820.map[i].addr > 0xFFFFFFFFUL)
-			continue;
-		/*
-		 * Don't MCR over reserved space. Ignore the ISA hole
-		 * we frob around that catastrophe already
-		 */
-		if (e820.map[i].type == E820_RESERVED) {
-			if (e820.map[i].addr >= 0x100000UL &&
-			    e820.map[i].addr < clip)
-				clip = e820.map[i].addr;
-			continue;
-		}
-		start = e820.map[i].addr;
-		end = e820.map[i].addr + e820.map[i].size;
-		if (start >= end)
-			continue;
-		if (end > top)
-			top = end;
-	}
-	/*
-	 * Everything below 'top' should be RAM except for the ISA hole.
-	 * Because of the limited MCR's we want to map NV/ACPI into our
-	 * MCR range for gunk in RAM
-	 *
-	 * Clip might cause us to MCR insufficient RAM but that is an
-	 * acceptable failure mode and should only bite obscure boxes with
-	 * a VESA hole at 15Mb
-	 *
-	 * The second case Clip sometimes kicks in is when the EBDA is marked
-	 * as reserved. Again we fail safe with reasonable results
-	 */
-	if (top > clip)
-		top = clip;
-
-	return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
-	u32 mem = ramtop();
-	u32 root = power2(mem);
-	u32 base = root;
-	u32 top = root;
-	u32 floor = 0;
-	int ct = 0;
-
-	while (ct < nr) {
-		u32 fspace = 0;
-		u32 high;
-		u32 low;
-
-		/*
-		 * Find the largest block we will fill going upwards
-		 */
-		high = power2(mem-top);
-
-		/*
-		 * Find the largest block we will fill going downwards
-		 */
-		low = base/2;
-
-		/*
-		 * Don't fill below 1Mb going downwards as there
-		 * is an ISA hole in the way.
-		 */
-		if (base <= 1024*1024)
-			low = 0;
-
-		/*
-		 * See how much space we could cover by filling below
-		 * the ISA hole
-		 */
-
-		if (floor == 0)
-			fspace = 512*1024;
-		else if (floor == 512*1024)
-			fspace = 128*1024;
-
-		/* And forget ROM space */
-
-		/*
-		 * Now install the largest coverage we get
-		 */
-		if (fspace > high && fspace > low) {
-			centaur_mcr_insert(ct, floor, fspace, key);
-			floor += fspace;
-		} else if (high > low) {
-			centaur_mcr_insert(ct, top, high, key);
-			top += high;
-		} else if (low > 0) {
-			base -= low;
-			centaur_mcr_insert(ct, base, low, key);
-		} else
-			break;
-		ct++;
-	}
-	/*
-	 * We loaded ct values. We now need to set the mask. The caller
-	 * must do this bit.
-	 */
-	return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
-	int used;
-	int i;
-
-	/*
-	 * Allocate up to 6 mcrs to mark as much of ram as possible
-	 * as write combining and weak write ordered.
-	 *
-	 * To experiment with: Linux never uses stack operations for
-	 * mmio spaces so we could globally enable stack operation wc
-	 *
-	 * Load the registers with type 31 - full write combining, all
-	 * writes weakly ordered.
-	 */
-	used = centaur_mcr_compute(6, 31);
-
-	/*
-	 * Wipe unused MCRs
-	 */
-	for (i = used; i < 8; i++)
-		wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
-	u32 lo, hi;
-	int used;
-	int i;
-
-	/*
-	 * Allocate up to 6 mcrs to mark as much of ram as possible
-	 * as write combining, weak store ordered.
-	 *
-	 * Load the registers with type 25
-	 *	8	-	weak write ordering
-	 *	16	-	weak read ordering
-	 *	1	-	write combining
-	 */
-	used = centaur_mcr_compute(6, 25);
-
-	/*
-	 * Mark the registers we are using.
-	 */
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	for (i = 0; i < used; i++)
-		lo |= 1<<(9+i);
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
-	/*
-	 * Wipe unused MCRs
-	 */
-
-	for (i = used; i < 8; i++)
-		wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
-	u32 lo, hi;
-	u32 key;
-
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	lo &= ~0x1C0;	/* blank bits 8-6 */
-	key = (lo>>17) & 7;
-	lo |= key<<6;	/* replace with unlock key */
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
-	u32 lo, hi;
-
-	rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-	lo &= ~0x1C0;	/* blank bits 8-6 */
-	wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
 #define ACE_PRESENT	(1 << 6)
 #define ACE_ENABLED	(1 << 7)
 #define ACE_FCR		(1 << 28)	/* MSR_VIA_FCR */
@@ -362,20 +132,6 @@
 			fcr_clr = DPDC;
 			printk(KERN_NOTICE "Disabling bugged TSC.\n");
 			clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
-			centaur_create_optimal_mcr();
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 *
-			 * The C6 original lacks weak read order
-			 *
-			 * Note 0x120 is write only on Winchip 1
-			 */
-			wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
 			break;
 		case 8:
 			switch (c->x86_mask) {
@@ -392,40 +148,12 @@
 			fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
 				  E2MMX|EAMD3D;
 			fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-			winchip2_unprotect_mcr();
-			winchip2_create_optimal_mcr();
-			rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 */
-			lo |= 31;
-			wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			winchip2_protect_mcr();
-#endif
 			break;
 		case 9:
 			name = "3";
 			fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
 				  E2MMX|EAMD3D;
 			fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-			winchip2_unprotect_mcr();
-			winchip2_create_optimal_mcr();
-			rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			/*
-			 * Enable:
-			 *	write combining on non-stack, non-string
-			 *	write combining on string, all types
-			 *	weak write ordering
-			 */
-			lo |= 31;
-			wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-			winchip2_protect_mcr();
-#endif
 			break;
 		default:
 			name = "??";
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 895604f..79f9f84 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1192,6 +1192,9 @@
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
 
+			if (i >= cpuc->n_events - cpuc->n_added)
+				--cpuc->n_added;
+
 			if (x86_pmu.put_event_constraints)
 				x86_pmu.put_event_constraints(cpuc, event);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c88f7f4..047f540 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -3334,6 +3334,8 @@
 	if (!pmus)
 		return -ENOMEM;
 
+	type->pmus = pmus;
+
 	type->unconstrainted = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
 				0, type->num_counters, 0, 0);
@@ -3369,7 +3371,6 @@
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
-	type->pmus = pmus;
 	return 0;
 fail:
 	uncore_type_exit(type);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba276..f36bd42 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@
 	/* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
 	cld
+
+	cmpl $2,(%esp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
 	incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@
 	pop %edx
 	pop %ecx
 	pop %eax
-	addl $8,%esp		/* drop vector number and error code */
 	decl %ss:early_recursion_flag
+is_nmi:
+	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb..a468c0a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@
 ENTRY(early_idt_handler)
 	cld
 
+	cmpl $2,(%rsp)		# X86_TRAP_NMI
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@
 	popq %rdx
 	popq %rcx
 	popq %rax
-	addq $16,%rsp		# drop vector number and error code
 	decl early_recursion_flag(%rip)
+is_nmi:
+	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6..d5dd808 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@
 
 void __kernel_fpu_end(void)
 {
-	if (use_eager_fpu())
-		math_state_restore();
-	else
+	if (use_eager_fpu()) {
+		/*
+		 * For eager fpu, most the time, tsk_used_math() is true.
+		 * Restore the user math as we are done with the kernel usage.
+		 * At few instances during thread exit, signal handling etc,
+		 * tsk_used_math() is false. Those few places will take proper
+		 * actions, so we don't need to restore the math here.
+		 */
+		if (likely(tsk_used_math(current)))
+			math_state_restore();
+	} else {
 		stts();
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc16..679cef0 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@
 	VMCOREINFO_SYMBOL(node_data);
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+			      (unsigned long)&_text - __START_KERNEL);
 }
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4..ff898bb 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@
 		return;
 
 	pci_read_config_dword(nb_ht, 0x60, &val);
-	node = val & 7;
+	node = pcibus_to_node(dev->bus) | (val & 7);
 	/*
 	 * Some hardware may return an invalid node ID,
 	 * so check it first:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e6..ce72964 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1239,14 +1239,8 @@
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, unmap the EFI memory map on
-	 * mismatched firmware/kernel archtectures since there is no
-	 * support for runtime services.
-	 */
-	if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
+	if (efi_enabled(EFI_BOOT))
+		efi_apply_memmap_quirks();
 #endif
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d..9b53135 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e81df8f..2de1bc0 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3002,10 +3002,8 @@
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(svm);
-	if (irqchip_in_kernel(svm->vcpu.kvm)) {
-		clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+	if (irqchip_in_kernel(svm->vcpu.kvm))
 		return r;
-	}
 	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
 		return r;
 	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3567,6 +3565,8 @@
 	if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
 		return;
 
+	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	if (irr == -1)
 		return;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101..3927528 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@
 		else if (is_page_fault(intr_info))
 			return enable_ept;
 		else if (is_no_device(intr_info) &&
-			 !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return 0;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09..2b85784 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@
 		frag->len -= len;
 	}
 
-	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 
 		/* FIXME: return into emulator if single-stepping.  */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 6dea040..a10c8c7 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1020,13 +1020,17 @@
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
  */
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
-	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1034,9 +1038,6 @@
 	tsk = current;
 	mm = tsk->mm;
 
-	/* Get the faulting address: */
-	address = read_cr2();
-
 	/*
 	 * Detect and handle instructions that would cause a page fault for
 	 * both a tracked kernel page and a userspace page.
@@ -1248,32 +1249,50 @@
 	up_read(&mm->mmap_sem);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	unsigned long address = read_cr2(); /* Get the faulting address */
 	enum ctx_state prev_state;
 
+	/*
+	 * We must have this function tagged with __kprobes, notrace and call
+	 * read_cr2() before calling anything else. To avoid calling any kind
+	 * of tracing machinery before we've observed the CR2 value.
+	 *
+	 * exception_{enter,exit}() contain all sorts of tracepoints.
+	 */
+
 	prev_state = exception_enter();
-	__do_page_fault(regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
 
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
 				     unsigned long error_code)
 {
 	if (user_mode(regs))
-		trace_page_fault_user(read_cr2(), regs, error_code);
+		trace_page_fault_user(address, regs, error_code);
 	else
-		trace_page_fault_kernel(read_cr2(), regs, error_code);
+		trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+	/*
+	 * The exception_enter and tracepoint processing could
+	 * trigger another page faults (user space callchain
+	 * reading) and destroy the original cr2 value, so read
+	 * the faulting address now.
+	 */
+	unsigned long address = read_cr2();
 	enum ctx_state prev_state;
 
 	prev_state = exception_enter();
-	trace_page_fault_entries(regs, error_code);
-	__do_page_fault(regs, error_code);
+	trace_page_fault_entries(address, regs, error_code);
+	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1..0149575 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@
 	push	%r9;						\
 	push	SKBDATA;					\
 /* rsi already has offset */					\
-	mov	$SIZE,%ecx;	/* size */			\
+	mov	$SIZE,%edx;	/* size */			\
 	call	bpf_internal_load_pointer_neg_helper;		\
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1a201ac..b97acec 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
+#include <asm/uv/uv.h>
 
 #define EFI_DEBUG
 
@@ -1210,3 +1211,22 @@
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_is_native()) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+}
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7d01b8c..cc04e67 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -40,11 +40,7 @@
 #define smp_rmb()	barrier()
 #endif /* CONFIG_X86_PPRO_FENCE */
 
-#ifdef CONFIG_X86_OOSTORE
-#define smp_wmb()	wmb()
-#else /* CONFIG_X86_OOSTORE */
 #define smp_wmb()	barrier()
-#endif /* CONFIG_X86_OOSTORE */
 
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index ba56e11..c87ae7c 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@
 	select HAVE_FUNCTION_TRACER
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_PERF_EVENTS
+	select COMMON_CLK
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
 	  primarily for embedded systems.  These processors are both
@@ -80,7 +81,6 @@
 config XTENSA_VARIANT_FSF
 	bool "fsf - default (not generic) configuration"
 	select MMU
-	select HAVE_XTENSA_GPIO32
 
 config XTENSA_VARIANT_DC232B
 	bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
@@ -135,7 +135,6 @@
 config SMP
 	bool "Enable Symmetric multi-processing support"
 	depends on HAVE_SMP
-	select USE_GENERIC_SMP_HELPERS
 	select GENERIC_SMP_IDLE_THREAD
 	help
 	  Enabled SMP Software; allows more than one CPU/CORE
diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi
index 46b4f5e..e7370b1 100644
--- a/arch/xtensa/boot/dts/xtfpga.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga.dtsi
@@ -35,6 +35,13 @@
 		interrupt-controller;
 	};
 
+	clocks {
+		osc: main-oscillator {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+		};
+	};
+
 	serial0: serial@fd050020 {
 		device_type = "serial";
 		compatible = "ns16550a";
@@ -42,9 +49,7 @@
 		reg = <0xfd050020 0x20>;
 		reg-shift = <2>;
 		interrupts = <0 1>; /* external irq 0 */
-		/* Filled in by platform_setup from FPGA register
-		 * clock-frequency = <100000000>;
-		 */
+		clocks = <&osc>;
 	};
 
 	enet0: ethoc@fd030000 {
@@ -52,5 +57,6 @@
 		reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
 		interrupts = <1 1>; /* external irq 1 */
 		local-mac-address = [00 50 c2 13 6f 00];
+		clocks = <&osc>;
 	};
 };
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 2a042d4..7494420 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_MMU
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 extern unsigned long xtensa_kio_paddr;
 
 static inline unsigned long xtensa_get_kio_paddr(void)
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 8c194f6..677bfcf 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -23,25 +23,37 @@
 
 static inline void spill_registers(void)
 {
-
+#if XCHAL_NUM_AREGS > 16
 	__asm__ __volatile__ (
-		"movi	a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
-		"mov	a12, a0\n\t"
-		"rsr	a13, sar\n\t"
-		"xsr	a14, ps\n\t"
-		"movi	a0, _spill_registers\n\t"
-		"rsync\n\t"
-		"callx0 a0\n\t"
-		"mov	a0, a12\n\t"
-		"wsr	a13, sar\n\t"
-		"wsr	a14, ps\n\t"
-		: :
-#if defined(CONFIG_FRAME_POINTER)
-		: "a2", "a3", "a4",       "a11", "a12", "a13", "a14", "a15",
-#else
-		: "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+		"	call12	1f\n"
+		"	_j	2f\n"
+		"	retw\n"
+		"	.align	4\n"
+		"1:\n"
+		"	_entry	a1, 48\n"
+		"	addi	a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+		"	_entry	a1, 48\n"
+		"	mov	a12, a0\n"
+		"	.endr\n"
 #endif
-		  "memory");
+		"	_entry	a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+		"	mov	a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+		"	mov	a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+		"	mov	a4, a4\n"
+#endif
+		"	retw\n"
+		"2:\n"
+		: : : "a12", "a13", "memory");
+#else
+	__asm__ __volatile__ (
+		"	mov	a12, a12\n"
+		: : : "memory");
+#endif
 }
 
 #endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index 5791b45..f74ddfb 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -25,7 +25,7 @@
 #define XCHAL_KIO_DEFAULT_PADDR		0xf0000000
 #define XCHAL_KIO_SIZE			0x10000000
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 #define XCHAL_KIO_PADDR			xtensa_get_kio_paddr()
 #else
 #define XCHAL_KIO_PADDR			XCHAL_KIO_DEFAULT_PADDR
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fe..b939552 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -734,7 +734,12 @@
 #define __NR_accept4				333
 __SYSCALL(333, sys_accept4, 4)
 
-#define __NR_syscall_count			334
+#define __NR_sched_setattr			334
+__SYSCALL(334, sys_sched_setattr, 2)
+#define __NR_sched_getattr			335
+__SYSCALL(335, sys_sched_getattr, 3)
+
+#define __NR_syscall_count			336
 
 /*
  * sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 21dbe6b..ef7f499 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1081,34 +1081,202 @@
 
 	rsr	a0, sar
 	s32i	a3, a2, PT_AREG3
+	s32i	a0, a2, PT_SAR
+
+	/* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */
+
 	s32i	a4, a2, PT_AREG4
-	s32i	a0, a2, PT_AREG5	# store SAR to PT_AREG5
-
-	/* The spill routine might clobber a7, a11, and a15. */
-
 	s32i	a7, a2, PT_AREG7
+	s32i	a8, a2, PT_AREG8
 	s32i	a11, a2, PT_AREG11
+	s32i	a12, a2, PT_AREG12
 	s32i	a15, a2, PT_AREG15
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
+	/*
+	 * Rotate ws so that the current windowbase is at bit 0.
+	 * Assume ws = xxxwww1yy (www1 current window frame).
+	 * Rotate ws right so that a4 = yyxxxwww1.
+	 */
+
+	rsr	a0, windowbase
+	rsr	a3, windowstart		# a3 = xxxwww1yy
+	ssr	a0			# holds WB
+	slli	a0, a3, WSBITS
+	or	a3, a3, a0		# a3 = xxxwww1yyxxxwww1yy
+	srl	a3, a3			# a3 = 00xxxwww1yyxxxwww1
+
+	/* We are done if there are no more than the current register frame. */
+
+	extui	a3, a3, 1, WSBITS-1	# a3 = 0yyxxxwww
+	movi	a0, (1 << (WSBITS-1))
+	_beqz	a3, .Lnospill		# only one active frame? jump
+
+	/* We want 1 at the top, so that we return to the current windowbase */
+
+	or	a3, a3, a0		# 1yyxxxwww
+
+	/* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
+
+	wsr	a3, windowstart		# save shifted windowstart
+	neg	a0, a3
+	and	a3, a0, a3		# first bit set from right: 000010000
+
+	ffs_ws	a0, a3			# a0: shifts to skip empty frames
+	movi	a3, WSBITS
+	sub	a0, a3, a0		# WSBITS-a0:number of 0-bits from right
+	ssr	a0			# save in SAR for later.
+
+	rsr	a3, windowbase
+	add	a3, a3, a0
+	wsr	a3, windowbase
+	rsync
+
+	rsr	a3, windowstart
+	srl	a3, a3			# shift windowstart
+
+	/* WB is now just one frame below the oldest frame in the register
+	   window. WS is shifted so the oldest frame is in bit 0, thus, WB
+	   and WS differ by one 4-register frame. */
+
+	/* Save frames. Depending what call was used (call4, call8, call12),
+	 * we have to save 4,8. or 12 registers.
+	 */
+
+
+.Lloop: _bbsi.l	a3, 1, .Lc4
+	_bbci.l	a3, 2, .Lc12
+
+.Lc8:	s32e	a4, a13, -16
+	l32e	a4, a5, -12
+	s32e	a8, a4, -32
+	s32e	a5, a13, -12
+	s32e	a6, a13, -8
+	s32e	a7, a13, -4
+	s32e	a9, a4, -28
+	s32e	a10, a4, -24
+	s32e	a11, a4, -20
+	srli	a11, a3, 2		# shift windowbase by 2
+	rotw	2
+	_bnei	a3, 1, .Lloop
+	j	.Lexit
+
+.Lc4:	s32e	a4, a9, -16
+	s32e	a5, a9, -12
+	s32e	a6, a9, -8
+	s32e	a7, a9, -4
+
+	srli	a7, a3, 1
+	rotw	1
+	_bnei	a3, 1, .Lloop
+	j	.Lexit
+
+.Lc12:	_bbci.l	a3, 3, .Linvalid_mask	# bit 2 shouldn't be zero!
+
+	/* 12-register frame (call12) */
+
+	l32e	a0, a5, -12
+	s32e	a8, a0, -48
+	mov	a8, a0
+
+	s32e	a9, a8, -44
+	s32e	a10, a8, -40
+	s32e	a11, a8, -36
+	s32e	a12, a8, -32
+	s32e	a13, a8, -28
+	s32e	a14, a8, -24
+	s32e	a15, a8, -20
+	srli	a15, a3, 3
+
+	/* The stack pointer for a4..a7 is out of reach, so we rotate the
+	 * window, grab the stackpointer, and rotate back.
+	 * Alternatively, we could also use the following approach, but that
+	 * makes the fixup routine much more complicated:
+	 * rotw	1
+	 * s32e	a0, a13, -16
+	 * ...
+	 * rotw 2
+	 */
+
+	rotw	1
+	mov	a4, a13
+	rotw	-1
+
+	s32e	a4, a8, -16
+	s32e	a5, a8, -12
+	s32e	a6, a8, -8
+	s32e	a7, a8, -4
+
+	rotw	3
+
+	_beqi	a3, 1, .Lexit
+	j	.Lloop
+
+.Lexit:
+
+	/* Done. Do the final rotation and set WS */
+
+	rotw	1
+	rsr	a3, windowbase
+	ssl	a3
+	movi	a3, 1
+	sll	a3, a3
+	wsr	a3, windowstart
+.Lnospill:
 
 	/* Advance PC, restore registers and SAR, and return from exception. */
 
-	l32i	a3, a2, PT_AREG5
-	l32i	a4, a2, PT_AREG4
+	l32i	a3, a2, PT_SAR
 	l32i	a0, a2, PT_AREG0
 	wsr	a3, sar
 	l32i	a3, a2, PT_AREG3
 
 	/* Restore clobbered registers. */
 
+	l32i	a4, a2, PT_AREG4
 	l32i	a7, a2, PT_AREG7
+	l32i	a8, a2, PT_AREG8
 	l32i	a11, a2, PT_AREG11
+	l32i	a12, a2, PT_AREG12
 	l32i	a15, a2, PT_AREG15
 
 	movi	a2, 0
 	rfe
 
+.Linvalid_mask:
+
+	/* We get here because of an unrecoverable error in the window
+	 * registers, so set up a dummy frame and kill the user application.
+	 * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
+	 */
+
+	movi	a0, 1
+	movi	a1, 0
+
+	wsr	a0, windowstart
+	wsr	a1, windowbase
+	rsync
+
+	movi	a0, 0
+
+	rsr	a3, excsave1
+	l32i	a1, a3, EXC_TABLE_KSTK
+
+	movi	a4, (1 << PS_WOE_BIT) | LOCKLEVEL
+	wsr	a4, ps
+	rsync
+
+	movi	a6, SIGSEGV
+	movi	a4, do_exit
+	callx4	a4
+
+	/* shouldn't return, so panic */
+
+	wsr	a0, excsave1
+	movi	a0, unrecoverable_exception
+	callx0	a0		# should not return
+1:	j	1b
+
+
 ENDPROC(fast_syscall_spill_registers)
 
 /* Fixup handler.
@@ -1117,6 +1285,13 @@
  * We basically restore WINDOWBASE and WINDOWSTART to the condition when
  * we entered the spill routine and jump to the user exception handler.
  *
+ * Note that we only need to restore the bits in windowstart that have not
+ * been spilled yet by the _spill_register routine. Luckily, a3 contains a
+ * rotated windowstart with only those bits set for frames that haven't been
+ * spilled yet. Because a3 is rotated such that bit 0 represents the register
+ * frame for the current windowbase - 1, we need to rotate a3 left by the
+ * value of the current windowbase + 1 and move it to windowstart.
+ *
  * a0: value of depc, original value in depc
  * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
  * a3: exctable, original value in excsave1
@@ -1131,10 +1306,15 @@
 	/* We need to make sure the current registers (a0-a3) are preserved.
 	 * To do this, we simply set the bit for the current window frame
 	 * in WS, so that the exception handlers save them to the task stack.
+	 *
+	 * Note: we use a3 to set the windowbase, so we take a special care
+	 * of it, saving it in the original _spill_registers frame across
+	 * the exception handler call.
 	 */
 
 	xsr	a3, excsave1	# get spill-mask
 	slli	a3, a3, 1	# shift left by one
+	addi	a3, a3, 1	# set the bit for the current window frame
 
 	slli	a2, a3, 32-WSBITS
 	src	a2, a3, a2	# a2 = xxwww1yyxxxwww1yy......
@@ -1220,209 +1400,6 @@
 
 ENDPROC(fast_syscall_spill_registers_fixup_return)
 
-/*
- * spill all registers.
- *
- * This is not a real function. The following conditions must be met:
- *
- *  - must be called with call0.
- *  - uses a3, a4 and SAR.
- *  - the last 'valid' register of each frame are clobbered.
- *  - the caller must have registered a fixup handler
- *    (or be inside a critical section)
- *  - PS_EXCM must be set (PS_WOE cleared?)
- */
-
-ENTRY(_spill_registers)
-
-	/*
-	 * Rotate ws so that the current windowbase is at bit 0.
-	 * Assume ws = xxxwww1yy (www1 current window frame).
-	 * Rotate ws right so that a4 = yyxxxwww1.
-	 */
-
-	rsr	a4, windowbase
-	rsr	a3, windowstart		# a3 = xxxwww1yy
-	ssr	a4			# holds WB
-	slli	a4, a3, WSBITS
-	or	a3, a3, a4		# a3 = xxxwww1yyxxxwww1yy
-	srl	a3, a3			# a3 = 00xxxwww1yyxxxwww1
-
-	/* We are done if there are no more than the current register frame. */
-
-	extui	a3, a3, 1, WSBITS-1	# a3 = 0yyxxxwww
-	movi	a4, (1 << (WSBITS-1))
-	_beqz	a3, .Lnospill		# only one active frame? jump
-
-	/* We want 1 at the top, so that we return to the current windowbase */
-
-	or	a3, a3, a4		# 1yyxxxwww
-
-	/* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
-
-	wsr	a3, windowstart		# save shifted windowstart
-	neg	a4, a3
-	and	a3, a4, a3		# first bit set from right: 000010000
-
-	ffs_ws	a4, a3			# a4: shifts to skip empty frames
-	movi	a3, WSBITS
-	sub	a4, a3, a4		# WSBITS-a4:number of 0-bits from right
-	ssr	a4			# save in SAR for later.
-
-	rsr	a3, windowbase
-	add	a3, a3, a4
-	wsr	a3, windowbase
-	rsync
-
-	rsr	a3, windowstart
-	srl	a3, a3			# shift windowstart
-
-	/* WB is now just one frame below the oldest frame in the register
-	   window. WS is shifted so the oldest frame is in bit 0, thus, WB
-	   and WS differ by one 4-register frame. */
-
-	/* Save frames. Depending what call was used (call4, call8, call12),
-	 * we have to save 4,8. or 12 registers.
-	 */
-
-	_bbsi.l	a3, 1, .Lc4
-	_bbsi.l	a3, 2, .Lc8
-
-	/* Special case: we have a call12-frame starting at a4. */
-
-	_bbci.l	a3, 3, .Lc12	# bit 3 shouldn't be zero! (Jump to Lc12 first)
-
-	s32e	a4, a1, -16	# a1 is valid with an empty spill area
-	l32e	a4, a5, -12
-	s32e	a8, a4, -48
-	mov	a8, a4
-	l32e	a4, a1, -16
-	j	.Lc12c
-
-.Lnospill:
-	ret
-
-.Lloop: _bbsi.l	a3, 1, .Lc4
-	_bbci.l	a3, 2, .Lc12
-
-.Lc8:	s32e	a4, a13, -16
-	l32e	a4, a5, -12
-	s32e	a8, a4, -32
-	s32e	a5, a13, -12
-	s32e	a6, a13, -8
-	s32e	a7, a13, -4
-	s32e	a9, a4, -28
-	s32e	a10, a4, -24
-	s32e	a11, a4, -20
-
-	srli	a11, a3, 2		# shift windowbase by 2
-	rotw	2
-	_bnei	a3, 1, .Lloop
-
-.Lexit: /* Done. Do the final rotation, set WS, and return. */
-
-	rotw	1
-	rsr	a3, windowbase
-	ssl	a3
-	movi	a3, 1
-	sll	a3, a3
-	wsr	a3, windowstart
-	ret
-
-.Lc4:	s32e	a4, a9, -16
-	s32e	a5, a9, -12
-	s32e	a6, a9, -8
-	s32e	a7, a9, -4
-
-	srli	a7, a3, 1
-	rotw	1
-	_bnei	a3, 1, .Lloop
-	j	.Lexit
-
-.Lc12:	_bbci.l	a3, 3, .Linvalid_mask	# bit 2 shouldn't be zero!
-
-	/* 12-register frame (call12) */
-
-	l32e	a2, a5, -12
-	s32e	a8, a2, -48
-	mov	a8, a2
-
-.Lc12c: s32e	a9, a8, -44
-	s32e	a10, a8, -40
-	s32e	a11, a8, -36
-	s32e	a12, a8, -32
-	s32e	a13, a8, -28
-	s32e	a14, a8, -24
-	s32e	a15, a8, -20
-	srli	a15, a3, 3
-
-	/* The stack pointer for a4..a7 is out of reach, so we rotate the
-	 * window, grab the stackpointer, and rotate back.
-	 * Alternatively, we could also use the following approach, but that
-	 * makes the fixup routine much more complicated:
-	 * rotw	1
-	 * s32e	a0, a13, -16
-	 * ...
-	 * rotw 2
-	 */
-
-	rotw	1
-	mov	a5, a13
-	rotw	-1
-
-	s32e	a4, a9, -16
-	s32e	a5, a9, -12
-	s32e	a6, a9, -8
-	s32e	a7, a9, -4
-
-	rotw	3
-
-	_beqi	a3, 1, .Lexit
-	j	.Lloop
-
-.Linvalid_mask:
-
-	/* We get here because of an unrecoverable error in the window
-	 * registers. If we are in user space, we kill the application,
-	 * however, this condition is unrecoverable in kernel space.
-	 */
-
-	rsr	a0, ps
-	_bbci.l	a0, PS_UM_BIT, 1f
-
-	/* User space: Setup a dummy frame and kill application.
-	 * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
-	 */
-
-	movi	a0, 1
-	movi	a1, 0
-
-	wsr	a0, windowstart
-	wsr	a1, windowbase
-	rsync
-
-	movi	a0, 0
-
-	rsr	a3, excsave1
-	l32i	a1, a3, EXC_TABLE_KSTK
-
-	movi	a4, (1 << PS_WOE_BIT) | LOCKLEVEL
-	wsr	a4, ps
-	rsync
-
-	movi	a6, SIGSEGV
-	movi	a4, do_exit
-	callx4	a4
-
-1:	/* Kernel space: PANIC! */
-
-	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0		# should not return
-1:	j	1b
-
-ENDPROC(_spill_registers)
-
 #ifdef CONFIG_MMU
 /*
  * We should never get here. Bail out!
@@ -1794,6 +1771,43 @@
 
 ENDPROC(system_call)
 
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+	.macro	spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+	call12	1f
+	_j	2f
+	retw
+	.align	4
+1:
+	_entry	a1, 48
+	addi	a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+	.rept	(XCHAL_NUM_AREGS - 32) / 12
+	_entry	a1, 48
+	mov	a12, a0
+	.endr
+#endif
+	_entry	a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+	mov	a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+	mov	a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+	mov	a4, a4
+#endif
+	retw
+2:
+#else
+	mov	a12, a12
+#endif
+	.endm
 
 /*
  * Task switch.
@@ -1806,21 +1820,20 @@
 
 	entry	a1, 16
 
-	mov	a12, a2			# preserve 'prev' (a2)
-	mov	a13, a3			# and 'next' (a3)
+	mov	a10, a2			# preserve 'prev' (a2)
+	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
 	l32i	a5, a3, TASK_THREAD_INFO
 
-	save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-	s32i	a0, a12, THREAD_RA	# save return address
-	s32i	a1, a12, THREAD_SP	# save stack pointer
+	s32i	a0, a10, THREAD_RA	# save return address
+	s32i	a1, a10, THREAD_SP	# save stack pointer
 
 	/* Disable ints while we manipulate the stack pointer. */
 
-	movi	a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
-	xsr	a14, ps
+	rsil	a14, LOCKLEVEL
 	rsr	a3, excsave1
 	rsync
 	s32i	a3, a3, EXC_TABLE_FIXUP	/* enter critical section */
@@ -1835,7 +1848,7 @@
 
 	/* Flush register file. */
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
+	spill_registers_kernel
 
 	/* Set kernel stack (and leave critical section)
 	 * Note: It's save to set it here. The stack will not be overwritten
@@ -1851,13 +1864,13 @@
 
 	/* restore context of the task 'next' */
 
-	l32i	a0, a13, THREAD_RA	# restore return address
-	l32i	a1, a13, THREAD_SP	# restore stack pointer
+	l32i	a0, a11, THREAD_RA	# restore return address
+	l32i	a1, a11, THREAD_SP	# restore stack pointer
 
-	load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
 	wsr	a14, ps
-	mov	a2, a12			# return 'prev'
+	mov	a2, a10			# return 'prev'
 	rsync
 
 	retw
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 7d12af1..84fe931 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
+#include <linux/clk-provider.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
@@ -276,6 +277,7 @@
 
 static int __init xtensa_device_probe(void)
 {
+	of_clk_init(NULL);
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 08b769d..2a1823d 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -30,6 +30,7 @@
 #include <asm/platform.h>
 
 unsigned long ccount_freq;		/* ccount Hz */
+EXPORT_SYMBOL(ccount_freq);
 
 static cycle_t ccount_read(struct clocksource *cs)
 {
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index cb8fd44..f9e1ec3 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -235,7 +235,7 @@
 
 	/* Check for overflow/underflow exception, jump if overflow. */
 
-	_bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
+	bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
 
 	/*
 	 * Restart window underflow exception.
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 74a60c7..80b33ed 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -122,9 +122,7 @@
 EXPORT_SYMBOL(insl);
 
 extern long common_exception_return;
-extern long _spill_registers;
 EXPORT_SYMBOL(common_exception_return);
-EXPORT_SYMBOL(_spill_registers);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 479d753..aff108d 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -90,7 +90,7 @@
 
 
 /*
- * Initialize the bootmem system and give it all the memory we have available.
+ * Initialize the bootmem system and give it all low memory we have available.
  */
 
 void __init bootmem_init(void)
@@ -142,9 +142,14 @@
 
 	/* Add all remaining memory pieces into the bootmem map */
 
-	for (i=0; i<sysmem.nr_banks; i++)
-		free_bootmem(sysmem.bank[i].start,
-			     sysmem.bank[i].end - sysmem.bank[i].start);
+	for (i = 0; i < sysmem.nr_banks; i++) {
+		if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) {
+			unsigned long end = min(max_low_pfn << PAGE_SHIFT,
+						sysmem.bank[i].end);
+			free_bootmem(sysmem.bank[i].start,
+				     end - sysmem.bank[i].start);
+		}
+	}
 
 }
 
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 36ec171..861203e 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -39,7 +39,7 @@
 	set_itlbcfg_register(0);
 	set_dtlbcfg_register(0);
 #endif
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 	/*
 	 * Update the IO area mapping in case xtensa_kio_paddr has changed
 	 */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 8002278..57fd08b 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -135,11 +135,11 @@
 
 static int __init machine_setup(void)
 {
-	struct device_node *serial;
+	struct device_node *clock;
 	struct device_node *eth = NULL;
 
-	for_each_compatible_node(serial, NULL, "ns16550a")
-		update_clock_frequency(serial);
+	for_each_node_by_name(clock, "main-oscillator")
+		update_clock_frequency(clock);
 
 	if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc")))
 		update_local_mac(eth);
@@ -290,6 +290,7 @@
 	 * knows whether they set it correctly on the DIP switches.
 	 */
 	pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr);
+	ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR;
 
 	return 0;
 }
diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h
index bf40201..244cdea 100644
--- a/arch/xtensa/variants/fsf/include/variant/tie.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie.h
@@ -18,13 +18,6 @@
 #define XCHAL_CP_MASK			0x00	/* bitmask of all CPs by ID */
 #define XCHAL_CP_PORT_MASK		0x00	/* bitmask of only port CPs */
 
-/*  Basic parameters of each coprocessor:  */
-#define XCHAL_CP7_NAME			"XTIOP"
-#define XCHAL_CP7_IDENT			XTIOP
-#define XCHAL_CP7_SA_SIZE		0	/* size of state save area */
-#define XCHAL_CP7_SA_ALIGN		1	/* min alignment of save area */
-#define XCHAL_CP_ID_XTIOP		7	/* coprocessor ID (0..7) */
-
 /*  Filler info for unassigned coprocessors, to simplify arrays etc:  */
 #define XCHAL_NCP_SA_SIZE		0
 #define XCHAL_NCP_SA_ALIGN		1
@@ -42,6 +35,8 @@
 #define XCHAL_CP5_SA_ALIGN		1
 #define XCHAL_CP6_SA_SIZE		0
 #define XCHAL_CP6_SA_ALIGN		1
+#define XCHAL_CP7_SA_SIZE		0
+#define XCHAL_CP7_SA_ALIGN		1
 
 /*  Save area for non-coprocessor optional and custom (TIE) state:  */
 #define XCHAL_NCP_SA_SIZE		0
diff --git a/block/blk-exec.c b/block/blk-exec.c
index c68613b..dbf4502 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@
 	 * be resued after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(q, rq, at_head, true);
+		blk_mq_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 66e2b69..f598f79 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -137,7 +137,7 @@
 	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
-	blk_mq_run_request(rq, true, false);
+	blk_mq_insert_request(rq, false, true, false);
 }
 
 static bool blk_flush_queue_rq(struct request *rq)
@@ -411,7 +411,7 @@
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_run_request(rq, false, true);
+			blk_mq_insert_request(rq, false, false, true);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 3146bef..136ef86 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -11,7 +11,7 @@
 #include "blk-mq.h"
 
 static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
 
 static int blk_mq_main_cpu_notify(struct notifier_block *self,
 				  unsigned long action, void *hcpu)
@@ -19,12 +19,12 @@
 	unsigned int cpu = (unsigned long) hcpu;
 	struct blk_mq_cpu_notifier *notify;
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 
 	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
 		notify->notify(notify->data, action, cpu);
 
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 	return NOTIFY_OK;
 }
 
@@ -32,16 +32,16 @@
 {
 	BUG_ON(!notifier->notify);
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_del(&notifier->list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1fa9dd1..883f720 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -73,8 +73,8 @@
 		set_bit(ctx->index_hw, hctx->ctx_map);
 }
 
-static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
-				       bool reserved)
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+					      gfp_t gfp, bool reserved)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -193,12 +193,6 @@
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
 }
 
-static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
-					      gfp_t gfp, bool reserved)
-{
-	return blk_mq_alloc_rq(hctx, gfp, reserved);
-}
-
 static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 						   int rw, gfp_t gfp,
 						   bool reserved)
@@ -289,38 +283,10 @@
 	__blk_mq_free_request(hctx, ctx, rq);
 }
 
-static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
+bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes)
 {
-	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
-
-	if (unlikely(rq->cmd_flags & REQ_QUIET))
-		set_bit(BIO_QUIET, &bio->bi_flags);
-
-	/* don't actually finish bio if it's part of flush sequence */
-	if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
-		bio_endio(bio, error);
-}
-
-void blk_mq_end_io(struct request *rq, int error)
-{
-	struct bio *bio = rq->bio;
-	unsigned int bytes = 0;
-
-	trace_block_rq_complete(rq->q, rq);
-
-	while (bio) {
-		struct bio *next = bio->bi_next;
-
-		bio->bi_next = NULL;
-		bytes += bio->bi_iter.bi_size;
-		blk_mq_bio_endio(rq, bio, error);
-		bio = next;
-	}
-
-	blk_account_io_completion(rq, bytes);
+	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+		return true;
 
 	blk_account_io_done(rq);
 
@@ -328,8 +294,9 @@
 		rq->end_io(rq, error);
 	else
 		blk_mq_free_request(rq);
+	return false;
 }
-EXPORT_SYMBOL(blk_mq_end_io);
+EXPORT_SYMBOL(blk_mq_end_io_partial);
 
 static void __blk_mq_complete_request_remote(void *data)
 {
@@ -730,60 +697,27 @@
 	blk_mq_add_timer(rq);
 }
 
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool at_head, bool run_queue)
-{
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
-
-	ctx = rq->mq_ctx;
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
-		blk_insert_flush(rq);
-	} else {
-		current_ctx = blk_mq_get_ctx(q);
-
-		if (!cpu_online(ctx->cpu)) {
-			ctx = current_ctx;
-			hctx = q->mq_ops->map_queue(q, ctx->cpu);
-			rq->mq_ctx = ctx;
-		}
-		spin_lock(&ctx->lock);
-		__blk_mq_insert_request(hctx, rq, at_head);
-		spin_unlock(&ctx->lock);
-
-		blk_mq_put_ctx(current_ctx);
-	}
-
-	if (run_queue)
-		__blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+		bool async)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
+	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
 
 	current_ctx = blk_mq_get_ctx(q);
+	if (!cpu_online(ctx->cpu))
+		rq->mq_ctx = ctx = current_ctx;
 
-	ctx = rq->mq_ctx;
-	if (!cpu_online(ctx->cpu)) {
-		ctx = current_ctx;
-		rq->mq_ctx = ctx;
-	}
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	/* ctx->cpu might be offline */
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, false);
-	spin_unlock(&ctx->lock);
+	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
+		blk_insert_flush(rq);
+	} else {
+		spin_lock(&ctx->lock);
+		__blk_mq_insert_request(hctx, rq, at_head);
+		spin_unlock(&ctx->lock);
+	}
 
 	blk_mq_put_ctx(current_ctx);
 
@@ -926,6 +860,8 @@
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
+	if (is_sync)
+		rw |= REQ_SYNC;
 	trace_block_getrq(q, bio, rw);
 	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
 	if (likely(rq))
diff --git a/block/blk-mq.h b/block/blk-mq.h
index ed0035c..72beba1 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -23,7 +23,6 @@
 };
 
 void __blk_mq_complete_request(struct request *rq);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_init_flush(struct request_queue *q);
 void blk_mq_drain_queue(struct request_queue *q);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 959d41a..d7d32c2 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -67,6 +67,8 @@
 #define ACPI_EC_DELAY		500	/* Wait 500ms max. during EC ops */
 #define ACPI_EC_UDELAY_GLK	1000	/* Wait 1ms max. to get global lock */
 #define ACPI_EC_MSI_UDELAY	550	/* Wait 550us for MSI EC */
+#define ACPI_EC_CLEAR_MAX	100	/* Maximum number of events to query
+					 * when trying to clear the EC */
 
 enum {
 	EC_FLAGS_QUERY_PENDING,		/* Query is pending */
@@ -116,6 +118,7 @@
 static int EC_FLAGS_MSI; /* Out-of-spec MSI controller */
 static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */
 static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */
+static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
 
 /* --------------------------------------------------------------------------
                              Transaction Management
@@ -440,6 +443,29 @@
 
 EXPORT_SYMBOL(ec_get_handle);
 
+static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data);
+
+/*
+ * Clears stale _Q events that might have accumulated in the EC.
+ * Run with locked ec mutex.
+ */
+static void acpi_ec_clear(struct acpi_ec *ec)
+{
+	int i, status;
+	u8 value = 0;
+
+	for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
+		status = acpi_ec_query_unlocked(ec, &value);
+		if (status || !value)
+			break;
+	}
+
+	if (unlikely(i == ACPI_EC_CLEAR_MAX))
+		pr_warn("Warning: Maximum of %d stale EC events cleared\n", i);
+	else
+		pr_info("%d stale EC events cleared\n", i);
+}
+
 void acpi_ec_block_transactions(void)
 {
 	struct acpi_ec *ec = first_ec;
@@ -463,6 +489,10 @@
 	mutex_lock(&ec->mutex);
 	/* Allow transactions to be carried out again */
 	clear_bit(EC_FLAGS_BLOCKED, &ec->flags);
+
+	if (EC_FLAGS_CLEAR_ON_RESUME)
+		acpi_ec_clear(ec);
+
 	mutex_unlock(&ec->mutex);
 }
 
@@ -821,6 +851,13 @@
 
 	/* EC is fully operational, allow queries */
 	clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags);
+
+	/* Clear stale _Q events if hardware might require that */
+	if (EC_FLAGS_CLEAR_ON_RESUME) {
+		mutex_lock(&ec->mutex);
+		acpi_ec_clear(ec);
+		mutex_unlock(&ec->mutex);
+	}
 	return ret;
 }
 
@@ -922,6 +959,30 @@
 	return 0;
 }
 
+/*
+ * On some hardware it is necessary to clear events accumulated by the EC during
+ * sleep. These ECs stop reporting GPEs until they are manually polled, if too
+ * many events are accumulated. (e.g. Samsung Series 5/9 notebooks)
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=44161
+ *
+ * Ideally, the EC should also be instructed NOT to accumulate events during
+ * sleep (which Windows seems to do somehow), but the interface to control this
+ * behaviour is not known at this time.
+ *
+ * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx,
+ * however it is very likely that other Samsung models are affected.
+ *
+ * On systems which don't accumulate _Q events during sleep, this extra check
+ * should be harmless.
+ */
+static int ec_clear_on_resume(const struct dmi_system_id *id)
+{
+	pr_debug("Detected system needing EC poll on resume.\n");
+	EC_FLAGS_CLEAR_ON_RESUME = 1;
+	return 0;
+}
+
 static struct dmi_system_id ec_dmi_table[] __initdata = {
 	{
 	ec_skip_dsdt_scan, "Compal JFL92", {
@@ -965,6 +1026,9 @@
 	ec_validate_ecdt, "ASUS hardware", {
 	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."),
 	DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL},
+	{
+	ec_clear_on_resume, "Samsung hardware", {
+	DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL},
 	{},
 };
 
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 28baa05..84243c3 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -56,6 +56,12 @@
 	int target_state;		/* target T-state */
 };
 
+struct acpi_processor_throttling_arg {
+	struct acpi_processor *pr;
+	int target_state;
+	bool force;
+};
+
 #define THROTTLING_PRECHANGE       (1)
 #define THROTTLING_POSTCHANGE      (2)
 
@@ -1060,16 +1066,24 @@
 	return 0;
 }
 
+static long acpi_processor_throttling_fn(void *data)
+{
+	struct acpi_processor_throttling_arg *arg = data;
+	struct acpi_processor *pr = arg->pr;
+
+	return pr->throttling.acpi_processor_set_throttling(pr,
+			arg->target_state, arg->force);
+}
+
 int acpi_processor_set_throttling(struct acpi_processor *pr,
 						int state, bool force)
 {
-	cpumask_var_t saved_mask;
 	int ret = 0;
 	unsigned int i;
 	struct acpi_processor *match_pr;
 	struct acpi_processor_throttling *p_throttling;
+	struct acpi_processor_throttling_arg arg;
 	struct throttling_tstate t_state;
-	cpumask_var_t online_throttling_cpus;
 
 	if (!pr)
 		return -EINVAL;
@@ -1080,14 +1094,6 @@
 	if ((state < 0) || (state > (pr->throttling.state_count - 1)))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) {
-		free_cpumask_var(saved_mask);
-		return -ENOMEM;
-	}
-
 	if (cpu_is_offline(pr->id)) {
 		/*
 		 * the cpu pointed by pr->id is offline. Unnecessary to change
@@ -1096,17 +1102,15 @@
 		return -ENODEV;
 	}
 
-	cpumask_copy(saved_mask, &current->cpus_allowed);
 	t_state.target_state = state;
 	p_throttling = &(pr->throttling);
-	cpumask_and(online_throttling_cpus, cpu_online_mask,
-		    p_throttling->shared_cpu_map);
+
 	/*
 	 * The throttling notifier will be called for every
 	 * affected cpu in order to get one proper T-state.
 	 * The notifier event is THROTTLING_PRECHANGE.
 	 */
-	for_each_cpu(i, online_throttling_cpus) {
+	for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_PRECHANGE,
 							&t_state);
@@ -1118,21 +1122,18 @@
 	 * it can be called only for the cpu pointed by pr.
 	 */
 	if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) {
-		/* FIXME: use work_on_cpu() */
-		if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
-			/* Can't migrate to the pr->id CPU. Exit */
-			ret = -ENODEV;
-			goto exit;
-		}
-		ret = p_throttling->acpi_processor_set_throttling(pr,
-						t_state.target_state, force);
+		arg.pr = pr;
+		arg.target_state = state;
+		arg.force = force;
+		ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
 	} else {
 		/*
 		 * When the T-state coordination is SW_ALL or HW_ALL,
 		 * it is necessary to set T-state for every affected
 		 * cpus.
 		 */
-		for_each_cpu(i, online_throttling_cpus) {
+		for_each_cpu_and(i, cpu_online_mask,
+		    p_throttling->shared_cpu_map) {
 			match_pr = per_cpu(processors, i);
 			/*
 			 * If the pointer is invalid, we will report the
@@ -1153,13 +1154,12 @@
 					"on CPU %d\n", i));
 				continue;
 			}
-			t_state.cpu = i;
-			/* FIXME: use work_on_cpu() */
-			if (set_cpus_allowed_ptr(current, cpumask_of(i)))
-				continue;
-			ret = match_pr->throttling.
-				acpi_processor_set_throttling(
-				match_pr, t_state.target_state, force);
+
+			arg.pr = match_pr;
+			arg.target_state = state;
+			arg.force = force;
+			ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
+				&arg);
 		}
 	}
 	/*
@@ -1168,17 +1168,12 @@
 	 * affected cpu to update the T-states.
 	 * The notifier event is THROTTLING_POSTCHANGE
 	 */
-	for_each_cpu(i, online_throttling_cpus) {
+	for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE,
 							&t_state);
 	}
-	/* restore the previous state */
-	/* FIXME: use work_on_cpu() */
-	set_cpus_allowed_ptr(current, saved_mask);
-exit:
-	free_cpumask_var(online_throttling_cpus);
-	free_cpumask_var(saved_mask);
+
 	return ret;
 }
 
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index b7201fc..0bdacc5 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,18 +77,24 @@
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 		memory24 = &ares->data.memory24;
+		if (!memory24->address_length)
+			return false;
 		acpi_dev_get_memresource(res, memory24->minimum,
 					 memory24->address_length,
 					 memory24->write_protect);
 		break;
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 		memory32 = &ares->data.memory32;
+		if (!memory32->address_length)
+			return false;
 		acpi_dev_get_memresource(res, memory32->minimum,
 					 memory32->address_length,
 					 memory32->write_protect);
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
 		fixed_memory32 = &ares->data.fixed_memory32;
+		if (!fixed_memory32->address_length)
+			return false;
 		acpi_dev_get_memresource(res, fixed_memory32->address,
 					 fixed_memory32->address_length,
 					 fixed_memory32->write_protect);
@@ -144,12 +150,16 @@
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_IO:
 		io = &ares->data.io;
+		if (!io->address_length)
+			return false;
 		acpi_dev_get_ioresource(res, io->minimum,
 					io->address_length,
 					io->io_decode);
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_IO:
 		fixed_io = &ares->data.fixed_io;
+		if (!fixed_io->address_length)
+			return false;
 		acpi_dev_get_ioresource(res, fixed_io->address,
 					fixed_io->address_length,
 					ACPI_DECODE_10);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index b718806..c40fb2e 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -71,6 +71,17 @@
 	return 0;
 }
 
+static bool acpi_sleep_state_supported(u8 sleep_state)
+{
+	acpi_status status;
+	u8 type_a, type_b;
+
+	status = acpi_get_sleep_type_data(sleep_state, &type_a, &type_b);
+	return ACPI_SUCCESS(status) && (!acpi_gbl_reduced_hardware
+		|| (acpi_gbl_FADT.sleep_control.address
+			&& acpi_gbl_FADT.sleep_status.address));
+}
+
 #ifdef CONFIG_ACPI_SLEEP
 static u32 acpi_target_sleep_state = ACPI_STATE_S0;
 
@@ -604,15 +615,9 @@
 {
 	int i;
 
-	for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) {
-		acpi_status status;
-		u8 type_a, type_b;
-
-		status = acpi_get_sleep_type_data(i, &type_a, &type_b);
-		if (ACPI_SUCCESS(status)) {
+	for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++)
+		if (acpi_sleep_state_supported(i))
 			sleep_states[i] = 1;
-		}
-	}
 
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
@@ -740,11 +745,7 @@
 
 static void acpi_sleep_hibernate_setup(void)
 {
-	acpi_status status;
-	u8 type_a, type_b;
-
-	status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b);
-	if (ACPI_FAILURE(status))
+	if (!acpi_sleep_state_supported(ACPI_STATE_S4))
 		return;
 
 	hibernation_set_ops(old_suspend_ordering ?
@@ -793,8 +794,6 @@
 
 int __init acpi_sleep_init(void)
 {
-	acpi_status status;
-	u8 type_a, type_b;
 	char supported[ACPI_S_STATE_COUNT * 3 + 1];
 	char *pos = supported;
 	int i;
@@ -806,8 +805,7 @@
 	acpi_sleep_suspend_setup();
 	acpi_sleep_hibernate_setup();
 
-	status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b);
-	if (ACPI_SUCCESS(status)) {
+	if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
 		sleep_states[ACPI_STATE_S5] = 1;
 		pm_power_off_prepare = acpi_power_off_prepare;
 		pm_power_off = acpi_power_off;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 1a3dbd1..8cb2522 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4175,6 +4175,7 @@
 
 	/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
 	{ "ST1000LM024 HN-M101MBB", "2AR10001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+	{ "ST1000LM024 HN-M101MBB", "2BA30001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
 
 	/* Blacklist entries taken from Silicon Image 3124/3132
 	   Windows driver .inf file - also several Linux problem reports */
@@ -4224,7 +4225,7 @@
 
 	/* devices that don't properly handle queued TRIM commands */
 	{ "Micron_M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
-	{ "Crucial_CT???M500SSD1",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Crucial_CT???M500SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
 
 	/*
 	 * Some WD SATA-I drives spin up and down erratically when the link
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 8a97ddf..c30df50e 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1580,6 +1580,7 @@
 	switch (mode) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
 		kill_requests_without_uevent();
 		device_cache_fw_images();
 		break;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 8184451..422b7d8 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -874,7 +874,7 @@
 		/* Non-zero page count for non-head members of
 		 * compound pages is no longer allowed by the kernel.
 		 */
-		page = compound_trans_head(bv.bv_page);
+		page = compound_head(bv.bv_page);
 		atomic_inc(&page->_count);
 	}
 }
@@ -887,7 +887,7 @@
 	struct bvec_iter iter;
 
 	bio_for_each_segment(bv, bio, iter) {
-		page = compound_trans_head(bv.bv_page);
+		page = compound_head(bv.bv_page);
 		atomic_dec(&page->_count);
 	}
 }
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index b52e9a6..54174cb 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -53,7 +53,7 @@
 #define MTIP_FTL_REBUILD_TIMEOUT_MS	2400000
 
 /* unaligned IO handling */
-#define MTIP_MAX_UNALIGNED_SLOTS	8
+#define MTIP_MAX_UNALIGNED_SLOTS	2
 
 /* Macro to extract the tag bit number from a tag value. */
 #define MTIP_TAG_BIT(tag)	(tag & 0x1F)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 011e55d..51c557c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -612,6 +612,8 @@
 
 	disksize = PAGE_ALIGN(disksize);
 	meta = zram_meta_alloc(disksize);
+	if (!meta)
+		return -ENOMEM;
 	down_write(&zram->init_lock);
 	if (zram->init_done) {
 		up_write(&zram->init_lock);
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index bd313f7..c1af80b 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -242,7 +242,7 @@
 
 	irq = irq_of_parse_and_map(np, 0);
 	if (!irq)
-		return;
+		goto out_free_characteristics;
 
 	clk = at91_clk_register_master(pmc, irq, name, num_parents,
 				       parent_names, layout,
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 6a934a5..05e04ce 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -494,6 +494,9 @@
 
 static int __init nomadik_src_clk_init_debugfs(void)
 {
+	/* Vital for multiplatform */
+	if (!src_base)
+		return -ENODEV;
 	src_pcksr0_boot = readl(src_base + SRC_PCKSR0);
 	src_pcksr1_boot = readl(src_base + SRC_PCKSR1);
 	debugfs_create_file("nomadik-src-clk", S_IFREG | S_IRUGO,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 5517944..c42e608 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2226,24 +2226,25 @@
  */
 int __clk_get(struct clk *clk)
 {
-	if (clk && !try_module_get(clk->owner))
-		return 0;
+	if (clk) {
+		if (!try_module_get(clk->owner))
+			return 0;
 
-	kref_get(&clk->ref);
+		kref_get(&clk->ref);
+	}
 	return 1;
 }
 
 void __clk_put(struct clk *clk)
 {
-	if (WARN_ON_ONCE(IS_ERR(clk)))
+	if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
 		return;
 
 	clk_prepare_lock();
 	kref_put(&clk->ref, __clk_release);
 	clk_prepare_unlock();
 
-	if (clk)
-		module_put(clk->owner);
+	module_put(clk->owner);
 }
 
 /***        clk rate change notifiers        ***/
diff --git a/drivers/clk/keystone/gate.c b/drivers/clk/keystone/gate.c
index 17a5983..86f1e36 100644
--- a/drivers/clk/keystone/gate.c
+++ b/drivers/clk/keystone/gate.c
@@ -179,6 +179,7 @@
 
 	init.name = name;
 	init.ops = &clk_psc_ops;
+	init.flags = 0;
 	init.parent_names = (parent_name ? &parent_name : NULL);
 	init.num_parents = (parent_name ? 1 : 0);
 
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index 81a202d..bef198a 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -141,13 +141,6 @@
 	.num_ratios = ARRAY_SIZE(a370_coreclk_ratios),
 };
 
-static void __init a370_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &a370_coreclks);
-}
-CLK_OF_DECLARE(a370_core_clk, "marvell,armada-370-core-clock",
-	       a370_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -168,9 +161,15 @@
 	{ }
 };
 
-static void __init a370_clk_gating_init(struct device_node *np)
+static void __init a370_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, a370_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,armada-370-gating-clock");
+
+	mvebu_coreclk_setup(np, &a370_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, a370_gating_desc);
 }
-CLK_OF_DECLARE(a370_clk_gating, "marvell,armada-370-gating-clock",
-	       a370_clk_gating_init);
+CLK_OF_DECLARE(a370_clk, "marvell,armada-370-core-clock", a370_clk_init);
+
diff --git a/drivers/clk/mvebu/armada-xp.c b/drivers/clk/mvebu/armada-xp.c
index 9922c44..b309431 100644
--- a/drivers/clk/mvebu/armada-xp.c
+++ b/drivers/clk/mvebu/armada-xp.c
@@ -158,13 +158,6 @@
 	.num_ratios = ARRAY_SIZE(axp_coreclk_ratios),
 };
 
-static void __init axp_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &axp_coreclks);
-}
-CLK_OF_DECLARE(axp_core_clk, "marvell,armada-xp-core-clock",
-	       axp_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -202,9 +195,14 @@
 	{ }
 };
 
-static void __init axp_clk_gating_init(struct device_node *np)
+static void __init axp_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, axp_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,armada-xp-gating-clock");
+
+	mvebu_coreclk_setup(np, &axp_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, axp_gating_desc);
 }
-CLK_OF_DECLARE(axp_clk_gating, "marvell,armada-xp-gating-clock",
-	       axp_clk_gating_init);
+CLK_OF_DECLARE(axp_clk, "marvell,armada-xp-core-clock", axp_clk_init);
diff --git a/drivers/clk/mvebu/dove.c b/drivers/clk/mvebu/dove.c
index 38aee1e..b8c2424 100644
--- a/drivers/clk/mvebu/dove.c
+++ b/drivers/clk/mvebu/dove.c
@@ -154,12 +154,6 @@
 	.num_ratios = ARRAY_SIZE(dove_coreclk_ratios),
 };
 
-static void __init dove_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &dove_coreclks);
-}
-CLK_OF_DECLARE(dove_core_clk, "marvell,dove-core-clock", dove_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -186,9 +180,14 @@
 	{ }
 };
 
-static void __init dove_clk_gating_init(struct device_node *np)
+static void __init dove_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, dove_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,dove-gating-clock");
+
+	mvebu_coreclk_setup(np, &dove_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, dove_gating_desc);
 }
-CLK_OF_DECLARE(dove_clk_gating, "marvell,dove-gating-clock",
-	       dove_clk_gating_init);
+CLK_OF_DECLARE(dove_clk, "marvell,dove-core-clock", dove_clk_init);
diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c
index 2636a55..ddb666a 100644
--- a/drivers/clk/mvebu/kirkwood.c
+++ b/drivers/clk/mvebu/kirkwood.c
@@ -193,13 +193,6 @@
 	.num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios),
 };
 
-static void __init kirkwood_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &kirkwood_coreclks);
-}
-CLK_OF_DECLARE(kirkwood_core_clk, "marvell,kirkwood-core-clock",
-	       kirkwood_coreclk_init);
-
 static const struct coreclk_soc_desc mv88f6180_coreclks = {
 	.get_tclk_freq = kirkwood_get_tclk_freq,
 	.get_cpu_freq = mv88f6180_get_cpu_freq,
@@ -208,13 +201,6 @@
 	.num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios),
 };
 
-static void __init mv88f6180_coreclk_init(struct device_node *np)
-{
-	mvebu_coreclk_setup(np, &mv88f6180_coreclks);
-}
-CLK_OF_DECLARE(mv88f6180_core_clk, "marvell,mv88f6180-core-clock",
-	       mv88f6180_coreclk_init);
-
 /*
  * Clock Gating Control
  */
@@ -239,9 +225,21 @@
 	{ }
 };
 
-static void __init kirkwood_clk_gating_init(struct device_node *np)
+static void __init kirkwood_clk_init(struct device_node *np)
 {
-	mvebu_clk_gating_setup(np, kirkwood_gating_desc);
+	struct device_node *cgnp =
+		of_find_compatible_node(NULL, NULL, "marvell,kirkwood-gating-clock");
+
+
+	if (of_device_is_compatible(np, "marvell,mv88f6180-core-clock"))
+		mvebu_coreclk_setup(np, &mv88f6180_coreclks);
+	else
+		mvebu_coreclk_setup(np, &kirkwood_coreclks);
+
+	if (cgnp)
+		mvebu_clk_gating_setup(cgnp, kirkwood_gating_desc);
 }
-CLK_OF_DECLARE(kirkwood_clk_gating, "marvell,kirkwood-gating-clock",
-	       kirkwood_clk_gating_init);
+CLK_OF_DECLARE(kirkwood_clk, "marvell,kirkwood-core-clock",
+	       kirkwood_clk_init);
+CLK_OF_DECLARE(mv88f6180_clk, "marvell,mv88f6180-core-clock",
+	       kirkwood_clk_init);
diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c
index a59ec21..99c27b1 100644
--- a/drivers/clk/shmobile/clk-rcar-gen2.c
+++ b/drivers/clk/shmobile/clk-rcar-gen2.c
@@ -26,6 +26,8 @@
 	void __iomem *reg;
 };
 
+#define CPG_FRQCRB			0x00000004
+#define CPG_FRQCRB_KICK			BIT(31)
 #define CPG_SDCKCR			0x00000074
 #define CPG_PLL0CR			0x000000d8
 #define CPG_FRQCRC			0x000000e0
@@ -45,6 +47,7 @@
 struct cpg_z_clk {
 	struct clk_hw hw;
 	void __iomem *reg;
+	void __iomem *kick_reg;
 };
 
 #define to_z_clk(_hw)	container_of(_hw, struct cpg_z_clk, hw)
@@ -83,17 +86,45 @@
 {
 	struct cpg_z_clk *zclk = to_z_clk(hw);
 	unsigned int mult;
-	u32 val;
+	u32 val, kick;
+	unsigned int i;
 
 	mult = div_u64((u64)rate * 32, parent_rate);
 	mult = clamp(mult, 1U, 32U);
 
+	if (clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK)
+		return -EBUSY;
+
 	val = clk_readl(zclk->reg);
 	val &= ~CPG_FRQCRC_ZFC_MASK;
 	val |= (32 - mult) << CPG_FRQCRC_ZFC_SHIFT;
 	clk_writel(val, zclk->reg);
 
-	return 0;
+	/*
+	 * Set KICK bit in FRQCRB to update hardware setting and wait for
+	 * clock change completion.
+	 */
+	kick = clk_readl(zclk->kick_reg);
+	kick |= CPG_FRQCRB_KICK;
+	clk_writel(kick, zclk->kick_reg);
+
+	/*
+	 * Note: There is no HW information about the worst case latency.
+	 *
+	 * Using experimental measurements, it seems that no more than
+	 * ~10 iterations are needed, independently of the CPU rate.
+	 * Since this value might be dependant of external xtal rate, pll1
+	 * rate or even the other emulation clocks rate, use 1000 as a
+	 * "super" safe value.
+	 */
+	for (i = 1000; i; i--) {
+		if (!(clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK))
+			return 0;
+
+		cpu_relax();
+	}
+
+	return -ETIMEDOUT;
 }
 
 static const struct clk_ops cpg_z_clk_ops = {
@@ -120,6 +151,7 @@
 	init.num_parents = 1;
 
 	zclk->reg = cpg->reg + CPG_FRQCRC;
+	zclk->kick_reg = cpg->reg + CPG_FRQCRB;
 	zclk->hw.init = &init;
 
 	clk = clk_register(NULL, &zclk->hw);
@@ -186,7 +218,7 @@
 			     const char *name)
 {
 	const struct clk_div_table *table = NULL;
-	const char *parent_name = "main";
+	const char *parent_name;
 	unsigned int shift;
 	unsigned int mult = 1;
 	unsigned int div = 1;
@@ -201,23 +233,31 @@
 		 * the multiplier value.
 		 */
 		u32 value = clk_readl(cpg->reg + CPG_PLL0CR);
+		parent_name = "main";
 		mult = ((value >> 24) & ((1 << 7) - 1)) + 1;
 	} else if (!strcmp(name, "pll1")) {
+		parent_name = "main";
 		mult = config->pll1_mult / 2;
 	} else if (!strcmp(name, "pll3")) {
+		parent_name = "main";
 		mult = config->pll3_mult;
 	} else if (!strcmp(name, "lb")) {
+		parent_name = "pll1_div2";
 		div = cpg_mode & BIT(18) ? 36 : 24;
 	} else if (!strcmp(name, "qspi")) {
+		parent_name = "pll1_div2";
 		div = (cpg_mode & (BIT(3) | BIT(2) | BIT(1))) == BIT(2)
-		    ? 16 : 20;
+		    ? 8 : 10;
 	} else if (!strcmp(name, "sdh")) {
+		parent_name = "pll1_div2";
 		table = cpg_sdh_div_table;
 		shift = 8;
 	} else if (!strcmp(name, "sd0")) {
+		parent_name = "pll1_div2";
 		table = cpg_sd01_div_table;
 		shift = 4;
 	} else if (!strcmp(name, "sd1")) {
+		parent_name = "pll1_div2";
 		table = cpg_sd01_div_table;
 		shift = 0;
 	} else if (!strcmp(name, "z")) {
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 4d75b1f..290f9c1 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -59,7 +59,7 @@
 		return 0;
 
 	if (divider_ux1 > get_max_div(divider))
-		return -EINVAL;
+		return get_max_div(divider);
 
 	return divider_ux1;
 }
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index cf0c323..c39613c 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -180,9 +180,13 @@
 	tegra_clk_sbc6_8,
 	tegra_clk_sclk,
 	tegra_clk_sdmmc1,
+	tegra_clk_sdmmc1_8,
 	tegra_clk_sdmmc2,
+	tegra_clk_sdmmc2_8,
 	tegra_clk_sdmmc3,
+	tegra_clk_sdmmc3_8,
 	tegra_clk_sdmmc4,
+	tegra_clk_sdmmc4_8,
 	tegra_clk_se,
 	tegra_clk_soc_therm,
 	tegra_clk_sor0,
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 5c35885..1fa5c3f 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -371,9 +371,7 @@
 static const char *mux_pllm_pllc_pllp_plla_pllc2_c3_clkm[] = {
 	"pll_m", "pll_c", "pll_p", "pll_a", "pll_c2", "pll_c3", "clk_m"
 };
-static u32 mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx[] = {
-	[0] = 0, [1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 6,
-};
+#define mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx NULL
 
 static const char *mux_pllm_pllc2_c_c3_pllp_plla_pllc4[] = {
 	"pll_m", "pll_c2", "pll_c", "pll_c3", "pll_p", "pll_a_out0", "pll_c4",
@@ -465,6 +463,10 @@
 	MUX("adx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_ADX1, 180, TEGRA_PERIPH_ON_APB, tegra_clk_adx1),
 	MUX("amx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_AMX1, 185, TEGRA_PERIPH_ON_APB, tegra_clk_amx1),
 	MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2),
+	MUX8("sdmmc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC1, 14, 0, tegra_clk_sdmmc1_8),
+	MUX8("sdmmc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC2, 9, 0, tegra_clk_sdmmc2_8),
+	MUX8("sdmmc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC3, 69, 0, tegra_clk_sdmmc3_8),
+	MUX8("sdmmc4", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC4, 15, 0, tegra_clk_sdmmc4_8),
 	MUX8("sbc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC1, 41, TEGRA_PERIPH_ON_APB, tegra_clk_sbc1_8),
 	MUX8("sbc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC2, 44, TEGRA_PERIPH_ON_APB, tegra_clk_sbc2_8),
 	MUX8("sbc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC3, 46, TEGRA_PERIPH_ON_APB, tegra_clk_sbc3_8),
@@ -492,7 +494,7 @@
 	UART("uartb", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTB, 7, tegra_clk_uartb),
 	UART("uartc", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTC, 55, tegra_clk_uartc),
 	UART("uartd", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTD, 65, tegra_clk_uartd),
-	UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 65, tegra_clk_uarte),
+	UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 66, tegra_clk_uarte),
 	XUSB("xusb_host_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_HOST_SRC, 143, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_host_src),
 	XUSB("xusb_falcon_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_FALCON_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_falcon_src),
 	XUSB("xusb_fs_src", mux_clkm_48M_pllp_480M, CLK_SOURCE_XUSB_FS_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_fs_src),
diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c
index 05dce4a..feb3201 100644
--- a/drivers/clk/tegra/clk-tegra-super-gen4.c
+++ b/drivers/clk/tegra/clk-tegra-super-gen4.c
@@ -120,7 +120,7 @@
 					ARRAY_SIZE(cclk_lp_parents),
 					CLK_SET_RATE_PARENT,
 					clk_base + CCLKLP_BURST_POLICY,
-					0, 4, 8, 9, NULL);
+					TEGRA_DIVIDER_2, 4, 8, 9, NULL);
 		*dt_clk = clk;
 	}
 
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index 90d9d25..80431f0 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -682,12 +682,12 @@
 	[tegra_clk_timer] = { .dt_id = TEGRA114_CLK_TIMER, .present = true },
 	[tegra_clk_uarta] = { .dt_id = TEGRA114_CLK_UARTA, .present = true },
 	[tegra_clk_uartd] = { .dt_id = TEGRA114_CLK_UARTD, .present = true },
-	[tegra_clk_sdmmc2] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true },
+	[tegra_clk_sdmmc2_8] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA114_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA114_CLK_I2C1, .present = true },
 	[tegra_clk_ndflash] = { .dt_id = TEGRA114_CLK_NDFLASH, .present = true },
-	[tegra_clk_sdmmc1] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true },
-	[tegra_clk_sdmmc4] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true },
+	[tegra_clk_sdmmc1_8] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true },
+	[tegra_clk_sdmmc4_8] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA114_CLK_PWM, .present = true },
 	[tegra_clk_i2s0] = { .dt_id = TEGRA114_CLK_I2S0, .present = true },
 	[tegra_clk_i2s2] = { .dt_id = TEGRA114_CLK_I2S2, .present = true },
@@ -723,7 +723,7 @@
 	[tegra_clk_bsev] = { .dt_id = TEGRA114_CLK_BSEV, .present = true },
 	[tegra_clk_i2c3] = { .dt_id = TEGRA114_CLK_I2C3, .present = true },
 	[tegra_clk_sbc4_8] = { .dt_id = TEGRA114_CLK_SBC4, .present = true },
-	[tegra_clk_sdmmc3] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true },
+	[tegra_clk_sdmmc3_8] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true },
 	[tegra_clk_owr] = { .dt_id = TEGRA114_CLK_OWR, .present = true },
 	[tegra_clk_csite] = { .dt_id = TEGRA114_CLK_CSITE, .present = true },
 	[tegra_clk_la] = { .dt_id = TEGRA114_CLK_LA, .present = true },
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index aff86b5..166e02f 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -516,11 +516,11 @@
 };
 
 static struct tegra_clk_pll_freq_table pll_p_freq_table[] = {
-	{12000000, 216000000, 432, 12, 1, 8},
-	{13000000, 216000000, 432, 13, 1, 8},
-	{16800000, 216000000, 360, 14, 1, 8},
-	{19200000, 216000000, 360, 16, 1, 8},
-	{26000000, 216000000, 432, 26, 1, 8},
+	{12000000, 408000000, 408, 12, 0, 8},
+	{13000000, 408000000, 408, 13, 0, 8},
+	{16800000, 408000000, 340, 14, 0, 8},
+	{19200000, 408000000, 340, 16, 0, 8},
+	{26000000, 408000000, 408, 26, 0, 8},
 	{0, 0, 0, 0, 0, 0},
 };
 
@@ -570,6 +570,15 @@
 	.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_USE_LOCK,
 };
 
+static struct div_nmp plld_nmp = {
+	.divm_shift = 0,
+	.divm_width = 5,
+	.divn_shift = 8,
+	.divn_width = 11,
+	.divp_shift = 20,
+	.divp_width = 3,
+};
+
 static struct tegra_clk_pll_freq_table pll_d_freq_table[] = {
 	{12000000, 216000000, 864, 12, 4, 12},
 	{13000000, 216000000, 864, 13, 4, 12},
@@ -603,19 +612,18 @@
 	.lock_mask = PLL_BASE_LOCK,
 	.lock_enable_bit_idx = PLLDU_MISC_LOCK_ENABLE,
 	.lock_delay = 1000,
-	.div_nmp = &pllp_nmp,
+	.div_nmp = &plld_nmp,
 	.freq_table = pll_d_freq_table,
 	.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON |
 		 TEGRA_PLL_USE_LOCK,
 };
 
 static struct tegra_clk_pll_freq_table tegra124_pll_d2_freq_table[] = {
-	{ 12000000, 148500000,  99, 1, 8},
-	{ 12000000, 594000000,  99, 1, 1},
-	{ 13000000, 594000000,  91, 1, 1},      /* actual: 591.5 MHz */
-	{ 16800000, 594000000,  71, 1, 1},      /* actual: 596.4 MHz */
-	{ 19200000, 594000000,  62, 1, 1},      /* actual: 595.2 MHz */
-	{ 26000000, 594000000,  91, 2, 1},      /* actual: 591.5 MHz */
+	{ 12000000, 594000000,  99, 1, 2},
+	{ 13000000, 594000000,  91, 1, 2},      /* actual: 591.5 MHz */
+	{ 16800000, 594000000,  71, 1, 2},      /* actual: 596.4 MHz */
+	{ 19200000, 594000000,  62, 1, 2},      /* actual: 595.2 MHz */
+	{ 26000000, 594000000,  91, 2, 2},      /* actual: 591.5 MHz */
 	{ 0, 0, 0, 0, 0, 0 },
 };
 
@@ -753,21 +761,19 @@
 	[tegra_clk_rtc] = { .dt_id = TEGRA124_CLK_RTC, .present = true },
 	[tegra_clk_timer] = { .dt_id = TEGRA124_CLK_TIMER, .present = true },
 	[tegra_clk_uarta] = { .dt_id = TEGRA124_CLK_UARTA, .present = true },
-	[tegra_clk_sdmmc2] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
+	[tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true },
 	[tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true },
-	[tegra_clk_sdmmc1] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
-	[tegra_clk_sdmmc4] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
+	[tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
+	[tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true },
 	[tegra_clk_i2s2] = { .dt_id = TEGRA124_CLK_I2S2, .present = true },
-	[tegra_clk_gr2d] = { .dt_id = TEGRA124_CLK_GR_2D, .present = true },
 	[tegra_clk_usbd] = { .dt_id = TEGRA124_CLK_USBD, .present = true },
 	[tegra_clk_isp_8] = { .dt_id = TEGRA124_CLK_ISP, .present = true },
-	[tegra_clk_gr3d] = { .dt_id = TEGRA124_CLK_GR_3D, .present = true },
 	[tegra_clk_disp2] = { .dt_id = TEGRA124_CLK_DISP2, .present = true },
 	[tegra_clk_disp1] = { .dt_id = TEGRA124_CLK_DISP1, .present = true },
-	[tegra_clk_host1x] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true },
+	[tegra_clk_host1x_8] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true },
 	[tegra_clk_vcp] = { .dt_id = TEGRA124_CLK_VCP, .present = true },
 	[tegra_clk_i2s0] = { .dt_id = TEGRA124_CLK_I2S0, .present = true },
 	[tegra_clk_apbdma] = { .dt_id = TEGRA124_CLK_APBDMA, .present = true },
@@ -794,7 +800,7 @@
 	[tegra_clk_uartd] = { .dt_id = TEGRA124_CLK_UARTD, .present = true },
 	[tegra_clk_i2c3] = { .dt_id = TEGRA124_CLK_I2C3, .present = true },
 	[tegra_clk_sbc4] = { .dt_id = TEGRA124_CLK_SBC4, .present = true },
-	[tegra_clk_sdmmc3] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true },
+	[tegra_clk_sdmmc3_8] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true },
 	[tegra_clk_pcie] = { .dt_id = TEGRA124_CLK_PCIE, .present = true },
 	[tegra_clk_owr] = { .dt_id = TEGRA124_CLK_OWR, .present = true },
 	[tegra_clk_afi] = { .dt_id = TEGRA124_CLK_AFI, .present = true },
@@ -1286,9 +1292,9 @@
 	clk_register_clkdev(clk, "pll_d2", NULL);
 	clks[TEGRA124_CLK_PLL_D2] = clk;
 
-	/* PLLD2_OUT0 ?? */
+	/* PLLD2_OUT0 */
 	clk = clk_register_fixed_factor(NULL, "pll_d2_out0", "pll_d2",
-					CLK_SET_RATE_PARENT, 1, 2);
+					CLK_SET_RATE_PARENT, 1, 1);
 	clk_register_clkdev(clk, "pll_d2_out0", NULL);
 	clks[TEGRA124_CLK_PLL_D2_OUT0] = clk;
 
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index dbace15..dace2b1 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -574,6 +574,8 @@
 	[tegra_clk_tvdac] = { .dt_id = TEGRA20_CLK_TVDAC, .present = true },
 	[tegra_clk_vi_sensor] = { .dt_id = TEGRA20_CLK_VI_SENSOR, .present = true },
 	[tegra_clk_afi] = { .dt_id = TEGRA20_CLK_AFI, .present = true },
+	[tegra_clk_fuse] = { .dt_id = TEGRA20_CLK_FUSE, .present = true },
+	[tegra_clk_kfuse] = { .dt_id = TEGRA20_CLK_KFUSE, .present = true },
 };
 
 static unsigned long tegra20_clk_measure_input_freq(void)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index cb003a6..199b52b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1109,12 +1109,27 @@
 		goto err_set_policy_cpu;
 	}
 
+	/* related cpus should atleast have policy->cpus */
+	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+
+	/*
+	 * affected cpus must always be the one, which are online. We aren't
+	 * managing offline cpus here.
+	 */
+	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
+
+	if (!frozen) {
+		policy->user_policy.min = policy->min;
+		policy->user_policy.max = policy->max;
+	}
+
+	down_write(&policy->rwsem);
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus)
 		per_cpu(cpufreq_cpu_data, j) = policy;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (cpufreq_driver->get) {
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
 			pr_err("%s: ->get() failed\n", __func__);
@@ -1162,20 +1177,6 @@
 		}
 	}
 
-	/* related cpus should atleast have policy->cpus */
-	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
-
-	/*
-	 * affected cpus must always be the one, which are online. We aren't
-	 * managing offline cpus here.
-	 */
-	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
-
-	if (!frozen) {
-		policy->user_policy.min = policy->min;
-		policy->user_policy.max = policy->max;
-	}
-
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
 
@@ -1206,6 +1207,7 @@
 		policy->user_policy.policy = policy->policy;
 		policy->user_policy.governor = policy->governor;
 	}
+	up_write(&policy->rwsem);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 	up_read(&cpufreq_rwsem);
@@ -1546,23 +1548,16 @@
  */
 unsigned int cpufreq_get(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	unsigned int ret_freq = 0;
 
-	if (cpufreq_disabled() || !cpufreq_driver)
-		return -ENOENT;
+	if (policy) {
+		down_read(&policy->rwsem);
+		ret_freq = __cpufreq_get(cpu);
+		up_read(&policy->rwsem);
 
-	BUG_ON(!policy);
-
-	if (!down_read_trylock(&cpufreq_rwsem))
-		return 0;
-
-	down_read(&policy->rwsem);
-
-	ret_freq = __cpufreq_get(cpu);
-
-	up_read(&policy->rwsem);
-	up_read(&cpufreq_rwsem);
+		cpufreq_cpu_put(policy);
+	}
 
 	return ret_freq;
 }
@@ -2148,7 +2143,7 @@
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
-	if (cpufreq_driver->get) {
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		new_policy.cur = cpufreq_driver->get(cpu);
 		if (!policy->cur) {
 			pr_debug("Driver did not initialize current freq");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index e908161..2cd36b9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -39,9 +39,10 @@
 #define BYT_TURBO_RATIOS	0x66c
 
 
-#define FRAC_BITS 8
+#define FRAC_BITS 6
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
+#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS)
 
 static inline int32_t mul_fp(int32_t x, int32_t y)
 {
@@ -556,18 +557,20 @@
 static inline void intel_pstate_calc_busy(struct cpudata *cpu,
 					struct sample *sample)
 {
-	u64 core_pct;
-	u64 c0_pct;
+	int32_t core_pct;
+	int32_t c0_pct;
 
-	core_pct = div64_u64(sample->aperf * 100, sample->mperf);
+	core_pct = div_fp(int_tofp((sample->aperf)),
+			int_tofp((sample->mperf)));
+	core_pct = mul_fp(core_pct, int_tofp(100));
+	FP_ROUNDUP(core_pct);
 
-	c0_pct = div64_u64(sample->mperf * 100, sample->tsc);
+	c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc));
+
 	sample->freq = fp_toint(
-		mul_fp(int_tofp(cpu->pstate.max_pstate),
-			int_tofp(core_pct * 1000)));
+		mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
 
-	sample->core_pct_busy = mul_fp(int_tofp(core_pct),
-				div_fp(int_tofp(c0_pct + 1), int_tofp(100)));
+	sample->core_pct_busy = mul_fp(core_pct, c0_pct);
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
@@ -579,6 +582,10 @@
 	rdmsrl(MSR_IA32_MPERF, mperf);
 	tsc = native_read_tsc();
 
+	aperf = aperf >> FRAC_BITS;
+	mperf = mperf >> FRAC_BITS;
+	tsc = tsc >> FRAC_BITS;
+
 	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
 	cpu->samples[cpu->sample_ptr].aperf = aperf;
 	cpu->samples[cpu->sample_ptr].mperf = mperf;
@@ -610,7 +617,8 @@
 	core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
 	max_pstate = int_tofp(cpu->pstate.max_pstate);
 	current_pstate = int_tofp(cpu->pstate.current_pstate);
-	return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+	return FP_ROUNDUP(core_busy);
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 4e79183..19041ce 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -449,6 +449,7 @@
 	{ .compatible = "fsl,imx51-sdma", .data = &sdma_imx51, },
 	{ .compatible = "fsl,imx35-sdma", .data = &sdma_imx35, },
 	{ .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, },
+	{ .compatible = "fsl,imx25-sdma", .data = &sdma_imx25, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 8752918..4e3549a 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -77,7 +77,8 @@
 	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
 	for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
 		chan = ioat_chan_by_index(instance, bit);
-		tasklet_schedule(&chan->cleanup_task);
+		if (test_bit(IOAT_RUN, &chan->state))
+			tasklet_schedule(&chan->cleanup_task);
 	}
 
 	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -93,7 +94,8 @@
 {
 	struct ioat_chan_common *chan = data;
 
-	tasklet_schedule(&chan->cleanup_task);
+	if (test_bit(IOAT_RUN, &chan->state))
+		tasklet_schedule(&chan->cleanup_task);
 
 	return IRQ_HANDLED;
 }
@@ -116,7 +118,6 @@
 	chan->timer.function = device->timer_fn;
 	chan->timer.data = data;
 	tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
-	tasklet_disable(&chan->cleanup_task);
 }
 
 /**
@@ -354,13 +355,49 @@
 	writel(((u64) chan->completion_dma) >> 32,
 	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
-	tasklet_enable(&chan->cleanup_task);
+	set_bit(IOAT_RUN, &chan->state);
 	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
 	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
 		__func__, ioat->desccount);
 	return ioat->desccount;
 }
 
+void ioat_stop(struct ioat_chan_common *chan)
+{
+	struct ioatdma_device *device = chan->device;
+	struct pci_dev *pdev = device->pdev;
+	int chan_id = chan_num(chan);
+	struct msix_entry *msix;
+
+	/* 1/ stop irq from firing tasklets
+	 * 2/ stop the tasklet from re-arming irqs
+	 */
+	clear_bit(IOAT_RUN, &chan->state);
+
+	/* flush inflight interrupts */
+	switch (device->irq_mode) {
+	case IOAT_MSIX:
+		msix = &device->msix_entries[chan_id];
+		synchronize_irq(msix->vector);
+		break;
+	case IOAT_MSI:
+	case IOAT_INTX:
+		synchronize_irq(pdev->irq);
+		break;
+	default:
+		break;
+	}
+
+	/* flush inflight timers */
+	del_timer_sync(&chan->timer);
+
+	/* flush inflight tasklet runs */
+	tasklet_kill(&chan->cleanup_task);
+
+	/* final cleanup now that everything is quiesced and can't re-arm */
+	device->cleanup_fn((unsigned long) &chan->common);
+}
+
 /**
  * ioat1_dma_free_chan_resources - release all the descriptors
  * @chan: the channel to be cleaned
@@ -379,9 +416,7 @@
 	if (ioat->desccount == 0)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	ioat1_cleanup(ioat);
+	ioat_stop(chan);
 
 	/* Delay 100ms after reset to allow internal DMA logic to quiesce
 	 * before removing DMA descriptor resources.
@@ -526,8 +561,11 @@
 static void ioat1_cleanup_event(unsigned long data)
 {
 	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat1_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 11fb877..e982f00 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -356,6 +356,7 @@
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
 void ioat_kobject_del(struct ioatdma_device *device);
 int ioat_dma_setup_interrupts(struct ioatdma_device *device);
+void ioat_stop(struct ioat_chan_common *chan);
 extern const struct sysfs_ops ioat_sysfs_ops;
 extern struct ioat_sysfs_entry ioat_version_attr;
 extern struct ioat_sysfs_entry ioat_cap_attr;
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 5d3affe..8d10580 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -190,8 +190,11 @@
 void ioat2_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat2_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
@@ -553,10 +556,10 @@
 	ioat->issued = 0;
 	ioat->tail = 0;
 	ioat->alloc_order = order;
+	set_bit(IOAT_RUN, &chan->state);
 	spin_unlock_bh(&ioat->prep_lock);
 	spin_unlock_bh(&chan->cleanup_lock);
 
-	tasklet_enable(&chan->cleanup_task);
 	ioat2_start_null_desc(ioat);
 
 	/* check that we got off the ground */
@@ -566,7 +569,6 @@
 	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
 
 	if (is_ioat_active(status) || is_ioat_idle(status)) {
-		set_bit(IOAT_RUN, &chan->state);
 		return 1 << ioat->alloc_order;
 	} else {
 		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -809,11 +811,8 @@
 	if (!ioat->ring)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	device->cleanup_fn((unsigned long) c);
+	ioat_stop(chan);
 	device->reset_hw(chan);
-	clear_bit(IOAT_RUN, &chan->state);
 
 	spin_lock_bh(&chan->cleanup_lock);
 	spin_lock_bh(&ioat->prep_lock);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 820817e9..b9b38a1 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -464,8 +464,11 @@
 static void ioat3_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat3_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 00a2de9..bf18c78 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1641,6 +1641,7 @@
 	struct d40_chan *d40c = (struct d40_chan *) data;
 	struct d40_desc *d40d;
 	unsigned long flags;
+	bool callback_active;
 	dma_async_tx_callback callback;
 	void *callback_param;
 
@@ -1668,6 +1669,7 @@
 	}
 
 	/* Callback to client */
+	callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
 	callback = d40d->txd.callback;
 	callback_param = d40d->txd.callback_param;
 
@@ -1690,7 +1692,7 @@
 
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT))
+	if (callback_active && callback)
 		callback(callback_param);
 
 	return;
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index d63f479..57e96a3 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -943,33 +943,35 @@
 
 	/* Attempt to 'get' the MCH register we want */
 	pdev = NULL;
-	while (!pvt->pci_dev_16_1_fsb_addr_map ||
-	       !pvt->pci_dev_16_2_fsb_err_regs) {
-		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
-				      PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev);
-		if (!pdev) {
-			/* End of list, leave */
-			i7300_printk(KERN_ERR,
-				"'system address,Process Bus' "
-				"device not found:"
-				"vendor 0x%x device 0x%x ERR funcs "
-				"(broken BIOS?)\n",
-				PCI_VENDOR_ID_INTEL,
-				PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
-			goto error;
-		}
-
+	while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+				      PCI_DEVICE_ID_INTEL_I7300_MCH_ERR,
+				      pdev))) {
 		/* Store device 16 funcs 1 and 2 */
 		switch (PCI_FUNC(pdev->devfn)) {
 		case 1:
-			pvt->pci_dev_16_1_fsb_addr_map = pdev;
+			if (!pvt->pci_dev_16_1_fsb_addr_map)
+				pvt->pci_dev_16_1_fsb_addr_map =
+							pci_dev_get(pdev);
 			break;
 		case 2:
-			pvt->pci_dev_16_2_fsb_err_regs = pdev;
+			if (!pvt->pci_dev_16_2_fsb_err_regs)
+				pvt->pci_dev_16_2_fsb_err_regs =
+							pci_dev_get(pdev);
 			break;
 		}
 	}
 
+	if (!pvt->pci_dev_16_1_fsb_addr_map ||
+	    !pvt->pci_dev_16_2_fsb_err_regs) {
+		/* At least one device was not found */
+		i7300_printk(KERN_ERR,
+			"'system address,Process Bus' device not found:"
+			"vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n",
+			PCI_VENDOR_ID_INTEL,
+			PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
+		goto error;
+	}
+
 	edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s  %x:%x\n",
 		 pci_name(pvt->pci_dev_16_0_fsb_ctlr),
 		 pvt->pci_dev_16_0_fsb_ctlr->vendor,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 87533ca..d871275 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1334,14 +1334,19 @@
 	 * is at addr 8086:2c40, instead of 8086:2c41. So, we need
 	 * to probe for the alternate address in case of failure
 	 */
-	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev)
+	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) {
+		pci_dev_get(*prev);	/* pci_get_device will put it */
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev);
+	}
 
-	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev)
+	if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE &&
+	    !pdev) {
+		pci_dev_get(*prev);	/* pci_get_device will put it */
 		pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
 				      PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT,
 				      *prev);
+	}
 
 	if (!pdev) {
 		if (*prev) {
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index c20602f..98a14f6 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -222,27 +222,19 @@
 	struct snd_soc_dapm_context *dapm = arizona->dapm;
 	int ret;
 
-	mutex_lock(&dapm->card->dapm_mutex);
-
 	ret = snd_soc_dapm_force_enable_pin(dapm, widget);
 	if (ret != 0)
 		dev_warn(arizona->dev, "Failed to enable %s: %d\n",
 			 widget, ret);
 
-	mutex_unlock(&dapm->card->dapm_mutex);
-
 	snd_soc_dapm_sync(dapm);
 
 	if (!arizona->pdata.micd_force_micbias) {
-		mutex_lock(&dapm->card->dapm_mutex);
-
 		ret = snd_soc_dapm_disable_pin(arizona->dapm, widget);
 		if (ret != 0)
 			dev_warn(arizona->dev, "Failed to disable %s: %d\n",
 				 widget, ret);
 
-		mutex_unlock(&dapm->card->dapm_mutex);
-
 		snd_soc_dapm_sync(dapm);
 	}
 }
@@ -304,16 +296,12 @@
 				 ARIZONA_MICD_ENA, 0,
 				 &change);
 
-	mutex_lock(&dapm->card->dapm_mutex);
-
 	ret = snd_soc_dapm_disable_pin(dapm, widget);
 	if (ret != 0)
 		dev_warn(arizona->dev,
 			 "Failed to disable %s: %d\n",
 			 widget, ret);
 
-	mutex_unlock(&dapm->card->dapm_mutex);
-
 	snd_soc_dapm_sync(dapm);
 
 	if (info->micd_reva) {
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index de4aa40..2c6d5e1 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -916,7 +916,7 @@
 		old->config_rom_retries = 0;
 		fw_notice(card, "rediscovered device %s\n", dev_name(dev));
 
-		PREPARE_DELAYED_WORK(&old->work, fw_device_update);
+		old->workfn = fw_device_update;
 		fw_schedule_device_work(old, 0);
 
 		if (current_node == card->root_node)
@@ -1075,7 +1075,7 @@
 	if (atomic_cmpxchg(&device->state,
 			   FW_DEVICE_INITIALIZING,
 			   FW_DEVICE_RUNNING) == FW_DEVICE_GONE) {
-		PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+		device->workfn = fw_device_shutdown;
 		fw_schedule_device_work(device, SHUTDOWN_DELAY);
 	} else {
 		fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n",
@@ -1196,13 +1196,20 @@
 		  dev_name(&device->device), fw_rcode_string(ret));
  gone:
 	atomic_set(&device->state, FW_DEVICE_GONE);
-	PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+	device->workfn = fw_device_shutdown;
 	fw_schedule_device_work(device, SHUTDOWN_DELAY);
  out:
 	if (node_id == card->root_node->node_id)
 		fw_schedule_bm_work(card, 0);
 }
 
+static void fw_device_workfn(struct work_struct *work)
+{
+	struct fw_device *device = container_of(to_delayed_work(work),
+						struct fw_device, work);
+	device->workfn(work);
+}
+
 void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 {
 	struct fw_device *device;
@@ -1252,7 +1259,8 @@
 		 * power-up after getting plugged in.  We schedule the
 		 * first config rom scan half a second after bus reset.
 		 */
-		INIT_DELAYED_WORK(&device->work, fw_device_init);
+		device->workfn = fw_device_init;
+		INIT_DELAYED_WORK(&device->work, fw_device_workfn);
 		fw_schedule_device_work(device, INITIAL_DELAY);
 		break;
 
@@ -1268,7 +1276,7 @@
 		if (atomic_cmpxchg(&device->state,
 			    FW_DEVICE_RUNNING,
 			    FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_refresh);
+			device->workfn = fw_device_refresh;
 			fw_schedule_device_work(device,
 				device->is_local ? 0 : INITIAL_DELAY);
 		}
@@ -1283,7 +1291,7 @@
 		smp_wmb();  /* update node_id before generation */
 		device->generation = card->generation;
 		if (atomic_read(&device->state) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_update);
+			device->workfn = fw_device_update;
 			fw_schedule_device_work(device, 0);
 		}
 		break;
@@ -1308,7 +1316,7 @@
 		device = node->data;
 		if (atomic_xchg(&device->state,
 				FW_DEVICE_GONE) == FW_DEVICE_RUNNING) {
-			PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+			device->workfn = fw_device_shutdown;
 			fw_schedule_device_work(device,
 				list_empty(&card->link) ? 0 : SHUTDOWN_DELAY);
 		}
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 6b89598..4af0a7b 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -929,8 +929,6 @@
 	if (rcode == RCODE_COMPLETE) {
 		fwnet_transmit_packet_done(ptask);
 	} else {
-		fwnet_transmit_packet_failed(ptask);
-
 		if (printk_timed_ratelimit(&j,  1000) || rcode != last_rcode) {
 			dev_err(&ptask->dev->netdev->dev,
 				"fwnet_write_complete failed: %x (skipped %d)\n",
@@ -938,8 +936,10 @@
 
 			errors_skipped = 0;
 			last_rcode = rcode;
-		} else
+		} else {
 			errors_skipped++;
+		}
+		fwnet_transmit_packet_failed(ptask);
 	}
 }
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 6f74d8d..8db6632 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -290,7 +290,6 @@
 #define QUIRK_NO_MSI			0x10
 #define QUIRK_TI_SLLZ059		0x20
 #define QUIRK_IR_WAKE			0x40
-#define QUIRK_PHY_LCTRL_TIMEOUT		0x80
 
 /* In case of multiple matches in ohci_quirks[], only the first one is used. */
 static const struct {
@@ -303,10 +302,7 @@
 		QUIRK_BE_HEADERS},
 
 	{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
-		QUIRK_PHY_LCTRL_TIMEOUT | QUIRK_NO_MSI},
-
-	{PCI_VENDOR_ID_ATT, PCI_ANY_ID, PCI_ANY_ID,
-		QUIRK_PHY_LCTRL_TIMEOUT},
+		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
 		QUIRK_RESET_PACKET},
@@ -353,7 +349,6 @@
 	", disable MSI = "		__stringify(QUIRK_NO_MSI)
 	", TI SLLZ059 erratum = "	__stringify(QUIRK_TI_SLLZ059)
 	", IR wake unreliable = "	__stringify(QUIRK_IR_WAKE)
-	", phy LCtrl timeout = "	__stringify(QUIRK_PHY_LCTRL_TIMEOUT)
 	")");
 
 #define OHCI_PARAM_DEBUG_AT_AR		1
@@ -2299,9 +2294,6 @@
 	 * TI TSB82AA2 + TSB81BA3(A) cards signal LPS enabled early but
 	 * cannot actually use the phy at that time.  These need tens of
 	 * millisecods pause between LPS write and first phy access too.
-	 *
-	 * But do not wait for 50msec on Agere/LSI cards.  Their phy
-	 * arbitration state machine may time out during such a long wait.
 	 */
 
 	reg_write(ohci, OHCI1394_HCControlSet,
@@ -2309,11 +2301,8 @@
 		  OHCI1394_HCControl_postedWriteEnable);
 	flush_writes(ohci);
 
-	if (!(ohci->quirks & QUIRK_PHY_LCTRL_TIMEOUT))
+	for (lps = 0, i = 0; !lps && i < 3; i++) {
 		msleep(50);
-
-	for (lps = 0, i = 0; !lps && i < 150; i++) {
-		msleep(1);
 		lps = reg_read(ohci, OHCI1394_HCControlSet) &
 		      OHCI1394_HCControl_LPS;
 	}
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 281029d..7aef911 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -146,6 +146,7 @@
 	 */
 	int generation;
 	int retries;
+	work_func_t workfn;
 	struct delayed_work work;
 	bool has_sdev;
 	bool blocked;
@@ -864,7 +865,7 @@
 	/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
 	sbp2_set_busy_timeout(lu);
 
-	PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
+	lu->workfn = sbp2_reconnect;
 	sbp2_agent_reset(lu);
 
 	/* This was a re-login. */
@@ -918,7 +919,7 @@
 	 * If a bus reset happened, sbp2_update will have requeued
 	 * lu->work already.  Reset the work from reconnect to login.
 	 */
-	PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+	lu->workfn = sbp2_login;
 }
 
 static void sbp2_reconnect(struct work_struct *work)
@@ -952,7 +953,7 @@
 		    lu->retries++ >= 5) {
 			dev_err(tgt_dev(tgt), "failed to reconnect\n");
 			lu->retries = 0;
-			PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+			lu->workfn = sbp2_login;
 		}
 		sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5));
 
@@ -972,6 +973,13 @@
 	sbp2_conditionally_unblock(lu);
 }
 
+static void sbp2_lu_workfn(struct work_struct *work)
+{
+	struct sbp2_logical_unit *lu = container_of(to_delayed_work(work),
+						struct sbp2_logical_unit, work);
+	lu->workfn(work);
+}
+
 static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
 {
 	struct sbp2_logical_unit *lu;
@@ -998,7 +1006,8 @@
 	lu->blocked  = false;
 	++tgt->dont_block;
 	INIT_LIST_HEAD(&lu->orb_list);
-	INIT_DELAYED_WORK(&lu->work, sbp2_login);
+	lu->workfn = sbp2_login;
+	INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn);
 
 	list_add_tail(&lu->link, &tgt->lu_list);
 	return 0;
diff --git a/drivers/fmc/fmc-write-eeprom.c b/drivers/fmc/fmc-write-eeprom.c
index ee5b479..9bb2cbd 100644
--- a/drivers/fmc/fmc-write-eeprom.c
+++ b/drivers/fmc/fmc-write-eeprom.c
@@ -27,7 +27,7 @@
 /* The "file=" is like the generic "gateware=" used elsewhere */
 static char *fwe_file[FMC_MAX_CARDS];
 static int fwe_file_n;
-module_param_array_named(file, fwe_file, charp, &fwe_file_n, 444);
+module_param_array_named(file, fwe_file, charp, &fwe_file_n, 0444);
 
 static int fwe_run_tlv(struct fmc_device *fmc, const struct firmware *fw,
 	int write)
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index acf3a36..32982da 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -68,15 +68,7 @@
 {
 	struct armada_private *priv = dev->dev_private;
 
-	/*
-	 * Yes, we really must jump through these hoops just to store a
-	 * _pointer_ to something into the kfifo.  This is utterly insane
-	 * and idiotic, because it kfifo requires the _data_ pointed to by
-	 * the pointer const, not the pointer itself.  Not only that, but
-	 * you have to pass a pointer _to_ the pointer you want stored.
-	 */
-	const struct drm_framebuffer *silly_api_alert = fb;
-	WARN_ON(!kfifo_put(&priv->fb_unref, &silly_api_alert));
+	WARN_ON(!kfifo_put(&priv->fb_unref, fb));
 	schedule_work(&priv->fb_unref_work);
 }
 
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 4ea9b17..b824622 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -259,7 +259,9 @@
 
 	ret = ttm_bo_device_init(&ast->ttm.bdev,
 				 ast->ttm.bo_global_ref.ref.object,
-				 &ast_bo_driver, DRM_FILE_PAGE_OFFSET,
+				 &ast_bo_driver,
+				 dev->anon_inode->i_mapping,
+				 DRM_FILE_PAGE_OFFSET,
 				 true);
 	if (ret) {
 		DRM_ERROR("Error initialising bo driver; %d\n", ret);
@@ -324,7 +326,6 @@
 	}
 
 	astbo->bo.bdev = &ast->ttm.bdev;
-	astbo->bo.bdev->dev_mapping = dev->dev_mapping;
 
 	ast_ttm_placement(astbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig
index c8fcf12..5f8b0c2 100644
--- a/drivers/gpu/drm/bochs/Kconfig
+++ b/drivers/gpu/drm/bochs/Kconfig
@@ -2,6 +2,7 @@
 	tristate "DRM Support for bochs dispi vga interface (qemu stdvga)"
 	depends on DRM && PCI
 	select DRM_KMS_HELPER
+	select DRM_KMS_FB_HELPER
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
 	select FB_SYS_IMAGEBLIT
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index ce68587..f488be5 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -225,7 +225,9 @@
 
 	ret = ttm_bo_device_init(&bochs->ttm.bdev,
 				 bochs->ttm.bo_global_ref.ref.object,
-				 &bochs_bo_driver, DRM_FILE_PAGE_OFFSET,
+				 &bochs_bo_driver,
+				 bochs->dev->anon_inode->i_mapping,
+				 DRM_FILE_PAGE_OFFSET,
 				 true);
 	if (ret) {
 		DRM_ERROR("Error initialising bo driver; %d\n", ret);
@@ -359,7 +361,7 @@
 	}
 
 	bochsbo->bo.bdev = &bochs->ttm.bdev;
-	bochsbo->bo.bdev->dev_mapping = dev->dev_mapping;
+	bochsbo->bo.bdev->dev_mapping = dev->anon_inode->i_mapping;
 
 	bochs_ttm_placement(bochsbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 8b37c25..92e6b77 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -259,7 +259,9 @@
 
 	ret = ttm_bo_device_init(&cirrus->ttm.bdev,
 				 cirrus->ttm.bo_global_ref.ref.object,
-				 &cirrus_bo_driver, DRM_FILE_PAGE_OFFSET,
+				 &cirrus_bo_driver,
+				 dev->anon_inode->i_mapping,
+				 DRM_FILE_PAGE_OFFSET,
 				 true);
 	if (ret) {
 		DRM_ERROR("Error initialising bo driver; %d\n", ret);
@@ -329,7 +331,6 @@
 	}
 
 	cirrusbo->bo.bdev = &cirrus->ttm.bdev;
-	cirrusbo->bo.bdev->dev_mapping = dev->dev_mapping;
 
 	cirrus_ttm_placement(cirrusbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 3b7d32d..16ca28e 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -38,12 +38,15 @@
 #include <drm/drm_edid.h>
 #include <drm/drm_fourcc.h>
 
+#include "drm_crtc_internal.h"
+
 /**
  * drm_modeset_lock_all - take all modeset locks
  * @dev: drm device
  *
  * This function takes all modeset locks, suitable where a more fine-grained
- * scheme isn't (yet) implemented.
+ * scheme isn't (yet) implemented. Locks must be dropped with
+ * drm_modeset_unlock_all.
  */
 void drm_modeset_lock_all(struct drm_device *dev)
 {
@@ -59,6 +62,8 @@
 /**
  * drm_modeset_unlock_all - drop all modeset locks
  * @dev: device
+ *
+ * This function drop all modeset locks taken by drm_modeset_lock_all.
  */
 void drm_modeset_unlock_all(struct drm_device *dev)
 {
@@ -74,6 +79,8 @@
 /**
  * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked
  * @dev: device
+ *
+ * Useful as a debug assert.
  */
 void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
 {
@@ -215,6 +222,16 @@
 	{ DRM_MODE_ENCODER_DSI, "DSI" },
 };
 
+static const struct drm_prop_enum_list drm_subpixel_enum_list[] =
+{
+	{ SubPixelUnknown, "Unknown" },
+	{ SubPixelHorizontalRGB, "Horizontal RGB" },
+	{ SubPixelHorizontalBGR, "Horizontal BGR" },
+	{ SubPixelVerticalRGB, "Vertical RGB" },
+	{ SubPixelVerticalBGR, "Vertical BGR" },
+	{ SubPixelNone, "None" },
+};
+
 void drm_connector_ida_init(void)
 {
 	int i;
@@ -231,6 +248,15 @@
 		ida_destroy(&drm_connector_enum_list[i].ida);
 }
 
+/**
+ * drm_get_encoder_name - return a string for encoder
+ * @encoder: encoder to compute name of
+ *
+ * Note that the buffer used by this function is globally shared and owned by
+ * the function itself.
+ *
+ * FIXME: This isn't really multithreading safe.
+ */
 const char *drm_get_encoder_name(const struct drm_encoder *encoder)
 {
 	static char buf[32];
@@ -242,6 +268,15 @@
 }
 EXPORT_SYMBOL(drm_get_encoder_name);
 
+/**
+ * drm_get_connector_name - return a string for connector
+ * @connector: connector to compute name of
+ *
+ * Note that the buffer used by this function is globally shared and owned by
+ * the function itself.
+ *
+ * FIXME: This isn't really multithreading safe.
+ */
 const char *drm_get_connector_name(const struct drm_connector *connector)
 {
 	static char buf[32];
@@ -253,6 +288,13 @@
 }
 EXPORT_SYMBOL(drm_get_connector_name);
 
+/**
+ * drm_get_connector_status_name - return a string for connector status
+ * @status: connector status to compute name of
+ *
+ * In contrast to the other drm_get_*_name functions this one here returns a
+ * const pointer and hence is threadsafe.
+ */
 const char *drm_get_connector_status_name(enum drm_connector_status status)
 {
 	if (status == connector_status_connected)
@@ -264,11 +306,33 @@
 }
 EXPORT_SYMBOL(drm_get_connector_status_name);
 
+/**
+ * drm_get_subpixel_order_name - return a string for a given subpixel enum
+ * @order: enum of subpixel_order
+ *
+ * Note you could abuse this and return something out of bounds, but that
+ * would be a caller error.  No unscrubbed user data should make it here.
+ */
+const char *drm_get_subpixel_order_name(enum subpixel_order order)
+{
+	return drm_subpixel_enum_list[order].name;
+}
+EXPORT_SYMBOL(drm_get_subpixel_order_name);
+
 static char printable_char(int c)
 {
 	return isascii(c) && isprint(c) ? c : '?';
 }
 
+/**
+ * drm_get_format_name - return a string for drm fourcc format
+ * @format: format to compute name of
+ *
+ * Note that the buffer used by this function is globally shared and owned by
+ * the function itself.
+ *
+ * FIXME: This isn't really multithreading safe.
+ */
 const char *drm_get_format_name(uint32_t format)
 {
 	static char buf[32];
@@ -293,14 +357,16 @@
  * @obj_type: object type
  *
  * Create a unique identifier based on @ptr in @dev's identifier space.  Used
- * for tracking modes, CRTCs and connectors.
+ * for tracking modes, CRTCs and connectors. Note that despite the _get postfix
+ * modeset identifiers are _not_ reference counted. Hence don't use this for
+ * reference counted modeset objects like framebuffers.
  *
- * RETURNS:
+ * Returns:
  * New unique (relative to other objects in @dev) integer identifier for the
  * object.
  */
-static int drm_mode_object_get(struct drm_device *dev,
-			       struct drm_mode_object *obj, uint32_t obj_type)
+int drm_mode_object_get(struct drm_device *dev,
+			struct drm_mode_object *obj, uint32_t obj_type)
 {
 	int ret;
 
@@ -324,10 +390,12 @@
  * @dev: DRM device
  * @object: object to free
  *
- * Free @id from @dev's unique identifier pool.
+ * Free @id from @dev's unique identifier pool. Note that despite the _get
+ * postfix modeset identifiers are _not_ reference counted. Hence don't use this
+ * for reference counted modeset objects like framebuffers.
  */
-static void drm_mode_object_put(struct drm_device *dev,
-				struct drm_mode_object *object)
+void drm_mode_object_put(struct drm_device *dev,
+			 struct drm_mode_object *object)
 {
 	mutex_lock(&dev->mode_config.idr_mutex);
 	idr_remove(&dev->mode_config.crtc_idr, object->id);
@@ -377,7 +445,7 @@
  * since all the fb attributes are invariant over its lifetime, no further
  * locking but only correct reference counting is required.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, error code on failure.
  */
 int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
@@ -438,7 +506,7 @@
  *
  * If successful, this grabs an additional reference to the framebuffer -
  * callers need to make sure to eventually unreference the returned framebuffer
- * again.
+ * again, using @drm_framebuffer_unreference.
  */
 struct drm_framebuffer *drm_framebuffer_lookup(struct drm_device *dev,
 					       uint32_t id)
@@ -471,6 +539,8 @@
 /**
  * drm_framebuffer_reference - incr the fb refcnt
  * @fb: framebuffer
+ *
+ * This functions increments the fb's refcount.
  */
 void drm_framebuffer_reference(struct drm_framebuffer *fb)
 {
@@ -527,8 +597,9 @@
  * drm_framebuffer_cleanup - remove a framebuffer object
  * @fb: framebuffer to remove
  *
- * Cleanup references to a user-created framebuffer. This function is intended
- * to be used from the drivers ->destroy callback.
+ * Cleanup framebuffer. This function is intended to be used from the drivers
+ * ->destroy callback. It can also be used to clean up driver private
+ *  framebuffers embedded into a larger structure.
  *
  * Note that this function does not remove the fb from active usuage - if it is
  * still used anywhere, hilarity can ensue since userspace could call getfb on
@@ -621,7 +692,7 @@
  *
  * Inits a new object created as base part of a driver crtc object.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, error code on failure.
  */
 int drm_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
@@ -697,20 +768,6 @@
 }
 EXPORT_SYMBOL(drm_crtc_index);
 
-/**
- * drm_mode_probed_add - add a mode to a connector's probed mode list
- * @connector: connector the new mode
- * @mode: mode data
- *
- * Add @mode to @connector's mode list for later use.
- */
-void drm_mode_probed_add(struct drm_connector *connector,
-			 struct drm_display_mode *mode)
-{
-	list_add_tail(&mode->head, &connector->probed_modes);
-}
-EXPORT_SYMBOL(drm_mode_probed_add);
-
 /*
  * drm_mode_remove - remove and free a mode
  * @connector: connector list to modify
@@ -735,7 +792,7 @@
  * Initialises a preallocated connector. Connectors should be
  * subclassed as part of driver connector objects.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, error code on failure.
  */
 int drm_connector_init(struct drm_device *dev,
@@ -813,6 +870,14 @@
 }
 EXPORT_SYMBOL(drm_connector_cleanup);
 
+/**
+ * drm_connector_unplug_all - unregister connector userspace interfaces
+ * @dev: drm device
+ *
+ * This function unregisters all connector userspace interfaces in sysfs. Should
+ * be call when the device is disconnected, e.g. from an usb driver's
+ * ->disconnect callback.
+ */
 void drm_connector_unplug_all(struct drm_device *dev)
 {
 	struct drm_connector *connector;
@@ -824,6 +889,18 @@
 }
 EXPORT_SYMBOL(drm_connector_unplug_all);
 
+/**
+ * drm_bridge_init - initialize a drm transcoder/bridge
+ * @dev: drm device
+ * @bridge: transcoder/bridge to set up
+ * @funcs: bridge function table
+ *
+ * Initialises a preallocated bridge. Bridges should be
+ * subclassed as part of driver connector objects.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
 int drm_bridge_init(struct drm_device *dev, struct drm_bridge *bridge,
 		const struct drm_bridge_funcs *funcs)
 {
@@ -847,6 +924,12 @@
 }
 EXPORT_SYMBOL(drm_bridge_init);
 
+/**
+ * drm_bridge_cleanup - cleans up an initialised bridge
+ * @bridge: bridge to cleanup
+ *
+ * Cleans up the bridge but doesn't free the object.
+ */
 void drm_bridge_cleanup(struct drm_bridge *bridge)
 {
 	struct drm_device *dev = bridge->dev;
@@ -859,6 +942,19 @@
 }
 EXPORT_SYMBOL(drm_bridge_cleanup);
 
+/**
+ * drm_encoder_init - Init a preallocated encoder
+ * @dev: drm device
+ * @encoder: the encoder to init
+ * @funcs: callbacks for this encoder
+ * @encoder_type: user visible type of the encoder
+ *
+ * Initialises a preallocated encoder. Encoder should be
+ * subclassed as part of driver encoder objects.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
 int drm_encoder_init(struct drm_device *dev,
 		      struct drm_encoder *encoder,
 		      const struct drm_encoder_funcs *funcs,
@@ -886,6 +982,12 @@
 }
 EXPORT_SYMBOL(drm_encoder_init);
 
+/**
+ * drm_encoder_cleanup - cleans up an initialised encoder
+ * @encoder: encoder to cleanup
+ *
+ * Cleans up the encoder but doesn't free the object.
+ */
 void drm_encoder_cleanup(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
@@ -907,9 +1009,10 @@
  * @format_count: number of elements in @formats
  * @priv: plane is private (hidden from userspace)?
  *
- * Inits a new object created as base part of a driver plane object.
+ * Inits a preallocate plane object created as base part of a driver plane
+ * object.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, error code on failure.
  */
 int drm_plane_init(struct drm_device *dev, struct drm_plane *plane,
@@ -1010,50 +1113,6 @@
 }
 EXPORT_SYMBOL(drm_plane_force_disable);
 
-/**
- * drm_mode_create - create a new display mode
- * @dev: DRM device
- *
- * Create a new drm_display_mode, give it an ID, and return it.
- *
- * RETURNS:
- * Pointer to new mode on success, NULL on error.
- */
-struct drm_display_mode *drm_mode_create(struct drm_device *dev)
-{
-	struct drm_display_mode *nmode;
-
-	nmode = kzalloc(sizeof(struct drm_display_mode), GFP_KERNEL);
-	if (!nmode)
-		return NULL;
-
-	if (drm_mode_object_get(dev, &nmode->base, DRM_MODE_OBJECT_MODE)) {
-		kfree(nmode);
-		return NULL;
-	}
-
-	return nmode;
-}
-EXPORT_SYMBOL(drm_mode_create);
-
-/**
- * drm_mode_destroy - remove a mode
- * @dev: DRM device
- * @mode: mode to remove
- *
- * Free @mode's unique identifier, then free it.
- */
-void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode)
-{
-	if (!mode)
-		return;
-
-	drm_mode_object_put(dev, &mode->base);
-
-	kfree(mode);
-}
-EXPORT_SYMBOL(drm_mode_destroy);
-
 static int drm_mode_create_standard_connector_properties(struct drm_device *dev)
 {
 	struct drm_property *edid;
@@ -1257,6 +1316,10 @@
 	return 0;
 }
 
+/*
+ * NOTE: Driver's shouldn't ever call drm_mode_group_init_legacy_group - it is
+ * the drm core's responsibility to set up mode control groups.
+ */
 int drm_mode_group_init_legacy_group(struct drm_device *dev,
 				     struct drm_mode_group *group)
 {
@@ -1333,7 +1396,7 @@
  * Convert a drm_mode_modeinfo into a drm_display_mode structure to return to
  * the caller.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 static int drm_crtc_convert_umode(struct drm_display_mode *out,
@@ -1376,7 +1439,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_getresources(struct drm_device *dev, void *data,
@@ -1561,7 +1624,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_getcrtc(struct drm_device *dev,
@@ -1630,7 +1693,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_getconnector(struct drm_device *dev, void *data,
@@ -1765,6 +1828,19 @@
 	return ret;
 }
 
+/**
+ * drm_mode_getencoder - get encoder configuration
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Construct a encoder configuration structure to return to the user.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_getencoder(struct drm_device *dev, void *data,
 			struct drm_file *file_priv)
 {
@@ -1800,15 +1876,20 @@
 }
 
 /**
- * drm_mode_getplane_res - get plane info
+ * drm_mode_getplane_res - enumerate all plane resources
  * @dev: DRM device
  * @data: ioctl data
  * @file_priv: DRM file info
  *
- * Return an plane count and set of IDs.
+ * Construct a list of plane ids to return to the user.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
  */
 int drm_mode_getplane_res(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv)
+			  struct drm_file *file_priv)
 {
 	struct drm_mode_get_plane_res *plane_resp = data;
 	struct drm_mode_config *config;
@@ -1846,16 +1927,20 @@
 }
 
 /**
- * drm_mode_getplane - get plane info
+ * drm_mode_getplane - get plane configuration
  * @dev: DRM device
  * @data: ioctl data
  * @file_priv: DRM file info
  *
- * Return plane info, including formats supported, gamma size, any
- * current fb, etc.
+ * Construct a plane configuration structure to return to the user.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
  */
 int drm_mode_getplane(struct drm_device *dev, void *data,
-			struct drm_file *file_priv)
+		      struct drm_file *file_priv)
 {
 	struct drm_mode_get_plane *plane_resp = data;
 	struct drm_mode_object *obj;
@@ -1911,16 +1996,19 @@
 }
 
 /**
- * drm_mode_setplane - set up or tear down an plane
+ * drm_mode_setplane - configure a plane's configuration
  * @dev: DRM device
  * @data: ioctl data*
  * @file_priv: DRM file info
  *
- * Set plane info, including placement, fb, scaling, and other factors.
+ * Set plane configuration, including placement, fb, scaling, and other factors.
  * Or pass a NULL fb to disable.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
  */
 int drm_mode_setplane(struct drm_device *dev, void *data,
-			struct drm_file *file_priv)
+		      struct drm_file *file_priv)
 {
 	struct drm_mode_set_plane *plane_req = data;
 	struct drm_mode_object *obj;
@@ -2050,6 +2138,9 @@
  *
  * This is a little helper to wrap internal calls to the ->set_config driver
  * interface. The only thing it adds is correct refcounting dance.
+ * 
+ * Returns:
+ * Zero on success, errno on failure.
  */
 int drm_mode_set_config_internal(struct drm_mode_set *set)
 {
@@ -2134,7 +2225,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_setcrtc(struct drm_device *dev, void *data,
@@ -2336,8 +2427,23 @@
 	return ret;
 
 }
+
+
+/**
+ * drm_mode_cursor_ioctl - set CRTC's cursor configuration
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Set the cursor configuration based on user request.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_cursor_ioctl(struct drm_device *dev,
-			void *data, struct drm_file *file_priv)
+			  void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_cursor *req = data;
 	struct drm_mode_cursor2 new_req;
@@ -2348,6 +2454,21 @@
 	return drm_mode_cursor_common(dev, &new_req, file_priv);
 }
 
+/**
+ * drm_mode_cursor2_ioctl - set CRTC's cursor configuration
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Set the cursor configuration based on user request. This implements the 2nd
+ * version of the cursor ioctl, which allows userspace to additionally specify
+ * the hotspot of the pointer.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_cursor2_ioctl(struct drm_device *dev,
 			   void *data, struct drm_file *file_priv)
 {
@@ -2355,7 +2476,14 @@
 	return drm_mode_cursor_common(dev, req, file_priv);
 }
 
-/* Original addfb only supported RGB formats, so figure out which one */
+/**
+ * drm_mode_legacy_fb_format - compute drm fourcc code from legacy description
+ * @bpp: bits per pixels
+ * @depth: bit depth per pixel
+ *
+ * Computes a drm fourcc pixel format code for the given @bpp/@depth values.
+ * Useful in fbdev emulation code, since that deals in those values.
+ */
 uint32_t drm_mode_legacy_fb_format(uint32_t bpp, uint32_t depth)
 {
 	uint32_t fmt;
@@ -2397,11 +2525,12 @@
  * @data: data pointer for the ioctl
  * @file_priv: drm file for the ioctl call
  *
- * Add a new FB to the specified CRTC, given a user request.
+ * Add a new FB to the specified CRTC, given a user request. This is the
+ * original addfb ioclt which only supported RGB formats.
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_addfb(struct drm_device *dev,
@@ -2574,11 +2703,13 @@
  * @data: data pointer for the ioctl
  * @file_priv: drm file for the ioctl call
  *
- * Add a new FB to the specified CRTC, given a user request with format.
+ * Add a new FB to the specified CRTC, given a user request with format. This is
+ * the 2nd version of the addfb ioctl, which supports multi-planar framebuffers
+ * and uses fourcc codes as pixel format specifiers.
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_addfb2(struct drm_device *dev,
@@ -2638,7 +2769,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_rmfb(struct drm_device *dev,
@@ -2692,7 +2823,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 int drm_mode_getfb(struct drm_device *dev,
@@ -2736,6 +2867,25 @@
 	return ret;
 }
 
+/**
+ * drm_mode_dirtyfb_ioctl - flush frontbuffer rendering on an FB
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Lookup the FB and flush out the damaged area supplied by userspace as a clip
+ * rectangle list. Generic userspace which does frontbuffer rendering must call
+ * this ioctl to flush out the changes on manual-update display outputs, e.g.
+ * usb display-link, mipi manual update panels or edp panel self refresh modes.
+ *
+ * Modesetting drivers which always update the frontbuffer do not need to
+ * implement the corresponding ->dirty framebuffer callback.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
 			   void *data, struct drm_file *file_priv)
 {
@@ -2813,7 +2963,7 @@
  *
  * Called by the user via ioctl.
  *
- * RETURNS:
+ * Returns:
  * Zero on success, errno on failure.
  */
 void drm_fb_release(struct drm_file *priv)
@@ -2837,6 +2987,20 @@
 	mutex_unlock(&priv->fbs_lock);
 }
 
+/**
+ * drm_property_create - create a new property type
+ * @dev: drm device
+ * @flags: flags specifying the property type
+ * @name: name of the property
+ * @num_values: number of pre-defined values
+ *
+ * This creates a new generic drm property which can then be attached to a drm
+ * object with drm_object_attach_property. The returned property object must be
+ * freed with drm_property_destroy.
+ *
+ * Returns:
+ * A pointer to the newly created property on success, NULL on failure.
+ */
 struct drm_property *drm_property_create(struct drm_device *dev, int flags,
 					 const char *name, int num_values)
 {
@@ -2875,6 +3039,24 @@
 }
 EXPORT_SYMBOL(drm_property_create);
 
+/**
+ * drm_property_create - create a new enumeration property type
+ * @dev: drm device
+ * @flags: flags specifying the property type
+ * @name: name of the property
+ * @props: enumeration lists with property values
+ * @num_values: number of pre-defined values
+ *
+ * This creates a new generic drm property which can then be attached to a drm
+ * object with drm_object_attach_property. The returned property object must be
+ * freed with drm_property_destroy.
+ *
+ * Userspace is only allowed to set one of the predefined values for enumeration
+ * properties.
+ *
+ * Returns:
+ * A pointer to the newly created property on success, NULL on failure.
+ */
 struct drm_property *drm_property_create_enum(struct drm_device *dev, int flags,
 					 const char *name,
 					 const struct drm_prop_enum_list *props,
@@ -2903,6 +3085,24 @@
 }
 EXPORT_SYMBOL(drm_property_create_enum);
 
+/**
+ * drm_property_create - create a new bitmask property type
+ * @dev: drm device
+ * @flags: flags specifying the property type
+ * @name: name of the property
+ * @props: enumeration lists with property bitflags
+ * @num_values: number of pre-defined values
+ *
+ * This creates a new generic drm property which can then be attached to a drm
+ * object with drm_object_attach_property. The returned property object must be
+ * freed with drm_property_destroy.
+ *
+ * Compared to plain enumeration properties userspace is allowed to set any
+ * or'ed together combination of the predefined property bitflag values
+ *
+ * Returns:
+ * A pointer to the newly created property on success, NULL on failure.
+ */
 struct drm_property *drm_property_create_bitmask(struct drm_device *dev,
 					 int flags, const char *name,
 					 const struct drm_prop_enum_list *props,
@@ -2931,6 +3131,24 @@
 }
 EXPORT_SYMBOL(drm_property_create_bitmask);
 
+/**
+ * drm_property_create - create a new ranged property type
+ * @dev: drm device
+ * @flags: flags specifying the property type
+ * @name: name of the property
+ * @min: minimum value of the property
+ * @max: maximum value of the property
+ *
+ * This creates a new generic drm property which can then be attached to a drm
+ * object with drm_object_attach_property. The returned property object must be
+ * freed with drm_property_destroy.
+ *
+ * Userspace is allowed to set any interger value in the (min, max) range
+ * inclusive.
+ *
+ * Returns:
+ * A pointer to the newly created property on success, NULL on failure.
+ */
 struct drm_property *drm_property_create_range(struct drm_device *dev, int flags,
 					 const char *name,
 					 uint64_t min, uint64_t max)
@@ -2950,6 +3168,21 @@
 }
 EXPORT_SYMBOL(drm_property_create_range);
 
+/**
+ * drm_property_add_enum - add a possible value to an enumeration property
+ * @property: enumeration property to change
+ * @index: index of the new enumeration
+ * @value: value of the new enumeration
+ * @name: symbolic name of the new enumeration
+ *
+ * This functions adds enumerations to a property.
+ *
+ * It's use is deprecated, drivers should use one of the more specific helpers
+ * to directly create the property with all enumerations already attached.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
 int drm_property_add_enum(struct drm_property *property, int index,
 			  uint64_t value, const char *name)
 {
@@ -2989,6 +3222,14 @@
 }
 EXPORT_SYMBOL(drm_property_add_enum);
 
+/**
+ * drm_property_destroy - destroy a drm property
+ * @dev: drm device
+ * @property: property to destry
+ *
+ * This function frees a property including any attached resources like
+ * enumeration values.
+ */
 void drm_property_destroy(struct drm_device *dev, struct drm_property *property)
 {
 	struct drm_property_enum *prop_enum, *pt;
@@ -3006,6 +3247,16 @@
 }
 EXPORT_SYMBOL(drm_property_destroy);
 
+/**
+ * drm_object_attach_property - attach a property to a modeset object
+ * @obj: drm modeset object
+ * @property: property to attach
+ * @init_val: initial value of the property
+ *
+ * This attaches the given property to the modeset object with the given initial
+ * value. Currently this function cannot fail since the properties are stored in
+ * a statically sized array.
+ */
 void drm_object_attach_property(struct drm_mode_object *obj,
 				struct drm_property *property,
 				uint64_t init_val)
@@ -3026,6 +3277,19 @@
 }
 EXPORT_SYMBOL(drm_object_attach_property);
 
+/**
+ * drm_object_property_set_value - set the value of a property
+ * @obj: drm mode object to set property value for
+ * @property: property to set
+ * @val: value the property should be set to
+ *
+ * This functions sets a given property on a given object. This function only
+ * changes the software state of the property, it does not call into the
+ * driver's ->set_property callback.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
 int drm_object_property_set_value(struct drm_mode_object *obj,
 				  struct drm_property *property, uint64_t val)
 {
@@ -3042,6 +3306,20 @@
 }
 EXPORT_SYMBOL(drm_object_property_set_value);
 
+/**
+ * drm_object_property_get_value - retrieve the value of a property
+ * @obj: drm mode object to get property value from
+ * @property: property to retrieve
+ * @val: storage for the property value
+ *
+ * This function retrieves the softare state of the given property for the given
+ * property. Since there is no driver callback to retrieve the current property
+ * value this might be out of sync with the hardware, depending upon the driver
+ * and property.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
 int drm_object_property_get_value(struct drm_mode_object *obj,
 				  struct drm_property *property, uint64_t *val)
 {
@@ -3058,6 +3336,19 @@
 }
 EXPORT_SYMBOL(drm_object_property_get_value);
 
+/**
+ * drm_mode_getproperty_ioctl - get the current value of a connector's property
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This function retrieves the current value for an connectors's property.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_getproperty_ioctl(struct drm_device *dev,
 			       void *data, struct drm_file *file_priv)
 {
@@ -3196,6 +3487,20 @@
 	kfree(blob);
 }
 
+/**
+ * drm_mode_getblob_ioctl - get the contents of a blob property value
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This function retrieves the contents of a blob property. The value stored in
+ * an object's blob property is just a normal modeset object id.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_getblob_ioctl(struct drm_device *dev,
 			   void *data, struct drm_file *file_priv)
 {
@@ -3230,6 +3535,17 @@
 	return ret;
 }
 
+/**
+ * drm_mode_connector_update_edid_property - update the edid property of a connector
+ * @connector: drm connector
+ * @edid: new value of the edid property
+ *
+ * This function creates a new blob modeset object and assigns its id to the
+ * connector's edid property.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 					    struct edid *edid)
 {
@@ -3287,6 +3603,20 @@
 	}
 }
 
+/**
+ * drm_mode_connector_property_set_ioctl - set the current value of a connector property
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This function sets the current value for a connectors's property. It also
+ * calls into a driver's ->set_property callback to update the hardware state
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
 				       void *data, struct drm_file *file_priv)
 {
@@ -3353,6 +3683,21 @@
 	return ret;
 }
 
+/**
+ * drm_mode_getproperty_ioctl - get the current value of a object's property
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This function retrieves the current value for an object's property. Compared
+ * to the connector specific ioctl this one is extended to also work on crtc and
+ * plane objects.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv)
 {
@@ -3409,6 +3754,22 @@
 	return ret;
 }
 
+/**
+ * drm_mode_obj_set_property_ioctl - set the current value of an object's property
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This function sets the current value for an object's property. It also calls
+ * into a driver's ->set_property callback to update the hardware state.
+ * Compared to the connector specific ioctl this one is extended to also work on
+ * crtc and plane objects.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file_priv)
 {
@@ -3468,6 +3829,18 @@
 	return ret;
 }
 
+/**
+ * drm_mode_connector_attach_encoder - attach a connector to an encoder
+ * @connector: connector to attach
+ * @encoder: encoder to attach @connector to
+ *
+ * This function links up a connector to an encoder. Note that the routing
+ * restrictions between encoders and crtcs are exposed to userspace through the
+ * possible_clones and possible_crtcs bitmasks.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 				      struct drm_encoder *encoder)
 {
@@ -3483,23 +3856,20 @@
 }
 EXPORT_SYMBOL(drm_mode_connector_attach_encoder);
 
-void drm_mode_connector_detach_encoder(struct drm_connector *connector,
-				    struct drm_encoder *encoder)
-{
-	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == encoder->base.id) {
-			connector->encoder_ids[i] = 0;
-			if (connector->encoder == encoder)
-				connector->encoder = NULL;
-			break;
-		}
-	}
-}
-EXPORT_SYMBOL(drm_mode_connector_detach_encoder);
-
+/**
+ * drm_mode_crtc_set_gamma_size - set the gamma table size
+ * @crtc: CRTC to set the gamma table size for
+ * @gamma_size: size of the gamma table
+ *
+ * Drivers which support gamma tables should set this to the supported gamma
+ * table size when initializing the CRTC. Currently the drm core only supports a
+ * fixed gamma table size.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc,
-				  int gamma_size)
+				 int gamma_size)
 {
 	crtc->gamma_size = gamma_size;
 
@@ -3513,6 +3883,20 @@
 }
 EXPORT_SYMBOL(drm_mode_crtc_set_gamma_size);
 
+/**
+ * drm_mode_gamma_set_ioctl - set the gamma table
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Set the gamma table of a CRTC to the one passed in by the user. Userspace can
+ * inquire the required gamma table size through drm_mode_gamma_get_ioctl.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
@@ -3572,6 +3956,21 @@
 
 }
 
+/**
+ * drm_mode_gamma_get_ioctl - get the gamma table
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Copy the current gamma table into the storage provided. This also provides
+ * the gamma table size the driver expects, which can be used to size the
+ * allocated storage.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_gamma_get_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
@@ -3622,6 +4021,24 @@
 	return ret;
 }
 
+/**
+ * drm_mode_page_flip_ioctl - schedule an asynchronous fb update
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This schedules an asynchronous update on a given CRTC, called page flip.
+ * Optionally a drm event is generated to signal the completion of the event.
+ * Generic drivers cannot assume that a pageflip with changed framebuffer
+ * properties (including driver specific metadata like tiling layout) will work,
+ * but some drivers support e.g. pixel format changes through the pageflip
+ * ioctl.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_page_flip_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
@@ -3734,6 +4151,14 @@
 	return ret;
 }
 
+/**
+ * drm_mode_config_reset - call ->reset callbacks
+ * @dev: drm device
+ *
+ * This functions calls all the crtc's, encoder's and connector's ->reset
+ * callback. Drivers can use this in e.g. their driver load or resume code to
+ * reset hardware and software state.
+ */
 void drm_mode_config_reset(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
@@ -3757,16 +4182,66 @@
 }
 EXPORT_SYMBOL(drm_mode_config_reset);
 
+/**
+ * drm_mode_create_dumb_ioctl - create a dumb backing storage buffer
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This creates a new dumb buffer in the driver's backing storage manager (GEM,
+ * TTM or something else entirely) and returns the resulting buffer handle. This
+ * handle can then be wrapped up into a framebuffer modeset object.
+ *
+ * Note that userspace is not allowed to use such objects for render
+ * acceleration - drivers must create their own private ioctls for such a use
+ * case.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_create_dumb_ioctl(struct drm_device *dev,
 			       void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_create_dumb *args = data;
+	u32 cpp, stride, size;
 
 	if (!dev->driver->dumb_create)
 		return -ENOSYS;
+	if (!args->width || !args->height || !args->bpp)
+		return -EINVAL;
+
+	/* overflow checks for 32bit size calculations */
+	cpp = DIV_ROUND_UP(args->bpp, 8);
+	if (cpp > 0xffffffffU / args->width)
+		return -EINVAL;
+	stride = cpp * args->width;
+	if (args->height > 0xffffffffU / stride)
+		return -EINVAL;
+
+	/* test for wrap-around */
+	size = args->height * stride;
+	if (PAGE_ALIGN(size) == 0)
+		return -EINVAL;
+
 	return dev->driver->dumb_create(file_priv, dev, args);
 }
 
+/**
+ * drm_mode_mmap_dumb_ioctl - create an mmap offset for a dumb backing storage buffer
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * Allocate an offset in the drm device node's address space to be able to
+ * memory map a dumb buffer.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_mmap_dumb_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
@@ -3779,6 +4254,21 @@
 	return dev->driver->dumb_map_offset(file_priv, dev, args->handle, &args->offset);
 }
 
+/**
+ * drm_mode_destroy_dumb_ioctl - destroy a dumb backing strage buffer
+ * @dev: DRM device
+ * @data: ioctl data
+ * @file_priv: DRM file info
+ *
+ * This destroys the userspace handle for the given dumb backing storage buffer.
+ * Since buffer objects must be reference counted in the kernel a buffer object
+ * won't be immediately freed if a framebuffer modeset object still uses it.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
 int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
 				void *data, struct drm_file *file_priv)
 {
@@ -3790,9 +4280,14 @@
 	return dev->driver->dumb_destroy(file_priv, dev, args->handle);
 }
 
-/*
- * Just need to support RGB formats here for compat with code that doesn't
- * use pixel formats directly yet.
+/**
+ * drm_fb_get_bpp_depth - get the bpp/depth values for format
+ * @format: pixel format (DRM_FORMAT_*)
+ * @depth: storage for the depth value
+ * @bpp: storage for the bpp value
+ *
+ * This only supports RGB formats here for compat with code that doesn't use
+ * pixel formats directly yet.
  */
 void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
 			  int *bpp)
@@ -3864,7 +4359,7 @@
  * drm_format_num_planes - get the number of planes for format
  * @format: pixel format (DRM_FORMAT_*)
  *
- * RETURNS:
+ * Returns:
  * The number of planes used by the specified pixel format.
  */
 int drm_format_num_planes(uint32_t format)
@@ -3899,7 +4394,7 @@
  * @format: pixel format (DRM_FORMAT_*)
  * @plane: plane index
  *
- * RETURNS:
+ * Returns:
  * The bytes per pixel value for the specified plane.
  */
 int drm_format_plane_cpp(uint32_t format, int plane)
@@ -3945,7 +4440,7 @@
  * drm_format_horz_chroma_subsampling - get the horizontal chroma subsampling factor
  * @format: pixel format (DRM_FORMAT_*)
  *
- * RETURNS:
+ * Returns:
  * The horizontal chroma subsampling factor for the
  * specified pixel format.
  */
@@ -3980,7 +4475,7 @@
  * drm_format_vert_chroma_subsampling - get the vertical chroma subsampling factor
  * @format: pixel format (DRM_FORMAT_*)
  *
- * RETURNS:
+ * Returns:
  * The vertical chroma subsampling factor for the
  * specified pixel format.
  */
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index ea92b82..a855178 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -105,9 +105,6 @@
  * @maxX: max width for modes
  * @maxY: max height for modes
  *
- * LOCKING:
- * Caller must hold mode config lock.
- *
  * Based on the helper callbacks implemented by @connector try to detect all
  * valid modes.  Modes will first be added to the connector's probed_modes list,
  * then culled (based on validity and the @maxX, @maxY parameters) and put into
@@ -117,8 +114,8 @@
  * @connector vfunc for drivers that use the crtc helpers for output mode
  * filtering and detection.
  *
- * RETURNS:
- * Number of modes found on @connector.
+ * Returns:
+ * The number of modes found on @connector.
  */
 int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 					    uint32_t maxX, uint32_t maxY)
@@ -131,6 +128,8 @@
 	int mode_flags = 0;
 	bool verbose_prune = true;
 
+	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
+
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id,
 			drm_get_connector_name(connector));
 	/* set all modes to the unverified state */
@@ -176,8 +175,7 @@
 	drm_mode_connector_list_update(connector);
 
 	if (maxX && maxY)
-		drm_mode_validate_size(dev, &connector->modes, maxX,
-				       maxY, 0);
+		drm_mode_validate_size(dev, &connector->modes, maxX, maxY);
 
 	if (connector->interlace_allowed)
 		mode_flags |= DRM_MODE_FLAG_INTERLACE;
@@ -219,18 +217,19 @@
  * drm_helper_encoder_in_use - check if a given encoder is in use
  * @encoder: encoder to check
  *
- * LOCKING:
- * Caller must hold mode config lock.
+ * Checks whether @encoder is with the current mode setting output configuration
+ * in use by any connector. This doesn't mean that it is actually enabled since
+ * the DPMS state is tracked separately.
  *
- * Walk @encoders's DRM device's mode_config and see if it's in use.
- *
- * RETURNS:
- * True if @encoder is part of the mode_config, false otherwise.
+ * Returns:
+ * True if @encoder is used, false otherwise.
  */
 bool drm_helper_encoder_in_use(struct drm_encoder *encoder)
 {
 	struct drm_connector *connector;
 	struct drm_device *dev = encoder->dev;
+
+	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
 		if (connector->encoder == encoder)
 			return true;
@@ -242,19 +241,19 @@
  * drm_helper_crtc_in_use - check if a given CRTC is in a mode_config
  * @crtc: CRTC to check
  *
- * LOCKING:
- * Caller must hold mode config lock.
+ * Checks whether @crtc is with the current mode setting output configuration
+ * in use by any connector. This doesn't mean that it is actually enabled since
+ * the DPMS state is tracked separately.
  *
- * Walk @crtc's DRM device's mode_config and see if it's in use.
- *
- * RETURNS:
- * True if @crtc is part of the mode_config, false otherwise.
+ * Returns:
+ * True if @crtc is used, false otherwise.
  */
 bool drm_helper_crtc_in_use(struct drm_crtc *crtc)
 {
 	struct drm_encoder *encoder;
 	struct drm_device *dev = crtc->dev;
-	/* FIXME: Locking around list access? */
+
+	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
 		if (encoder->crtc == crtc && drm_helper_encoder_in_use(encoder))
 			return true;
@@ -283,11 +282,11 @@
  * drm_helper_disable_unused_functions - disable unused objects
  * @dev: DRM device
  *
- * LOCKING:
- * Caller must hold mode config lock.
- *
- * If an connector or CRTC isn't part of @dev's mode_config, it can be disabled
- * by calling its dpms function, which should power it off.
+ * This function walks through the entire mode setting configuration of @dev. It
+ * will remove any crtc links of unused encoders and encoder links of
+ * disconnected connectors. Then it will disable all unused encoders and crtcs
+ * either by calling their disable callback if available or by calling their
+ * dpms callback with DRM_MODE_DPMS_OFF.
  */
 void drm_helper_disable_unused_functions(struct drm_device *dev)
 {
@@ -295,6 +294,8 @@
 	struct drm_connector *connector;
 	struct drm_crtc *crtc;
 
+	drm_warn_on_modeset_not_all_locked(dev);
+
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		if (!connector->encoder)
 			continue;
@@ -355,9 +356,6 @@
  * @y: vertical offset into the surface
  * @old_fb: old framebuffer, for cleanup
  *
- * LOCKING:
- * Caller must hold mode config lock.
- *
  * Try to set @mode on @crtc.  Give @crtc and its associated connectors a chance
  * to fixup or reject the mode prior to trying to set it. This is an internal
  * helper that drivers could e.g. use to update properties that require the
@@ -367,8 +365,8 @@
  * drm_crtc_helper_set_config() helper function to drive the mode setting
  * sequence.
  *
- * RETURNS:
- * True if the mode was set successfully, or false otherwise.
+ * Returns:
+ * True if the mode was set successfully, false otherwise.
  */
 bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 			      struct drm_display_mode *mode,
@@ -384,6 +382,8 @@
 	struct drm_encoder *encoder;
 	bool ret = true;
 
+	drm_warn_on_modeset_not_all_locked(dev);
+
 	saved_enabled = crtc->enabled;
 	crtc->enabled = drm_helper_crtc_in_use(crtc);
 	if (!crtc->enabled)
@@ -560,17 +560,14 @@
  * drm_crtc_helper_set_config - set a new config from userspace
  * @set: mode set configuration
  *
- * LOCKING:
- * Caller must hold mode config lock.
- *
  * Setup a new configuration, provided by the upper layers (either an ioctl call
  * from userspace or internally e.g. from the fbdev suppport code) in @set, and
  * enable it. This is the main helper functions for drivers that implement
  * kernel mode setting with the crtc helper functions and the assorted
  * ->prepare(), ->modeset() and ->commit() helper callbacks.
  *
- * RETURNS:
- * Returns 0 on success, -ERRNO on failure.
+ * Returns:
+ * Returns 0 on success, negative errno numbers on failure.
  */
 int drm_crtc_helper_set_config(struct drm_mode_set *set)
 {
@@ -612,6 +609,8 @@
 
 	dev = set->crtc->dev;
 
+	drm_warn_on_modeset_not_all_locked(dev);
+
 	/*
 	 * Allocate space for the backup of all (non-pointer) encoder and
 	 * connector data.
@@ -924,8 +923,16 @@
 }
 EXPORT_SYMBOL(drm_helper_connector_dpms);
 
-int drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
-				   struct drm_mode_fb_cmd2 *mode_cmd)
+/**
+ * drm_helper_mode_fill_fb_struct - fill out framebuffer metadata
+ * @fb: drm_framebuffer object to fill out
+ * @mode_cmd: metadata from the userspace fb creation request
+ *
+ * This helper can be used in a drivers fb_create callback to pre-fill the fb's
+ * metadata fields.
+ */
+void drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
+				    struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	int i;
 
@@ -938,17 +945,36 @@
 	drm_fb_get_bpp_depth(mode_cmd->pixel_format, &fb->depth,
 				    &fb->bits_per_pixel);
 	fb->pixel_format = mode_cmd->pixel_format;
-
-	return 0;
 }
 EXPORT_SYMBOL(drm_helper_mode_fill_fb_struct);
 
-int drm_helper_resume_force_mode(struct drm_device *dev)
+/**
+ * drm_helper_resume_force_mode - force-restore mode setting configuration
+ * @dev: drm_device which should be restored
+ *
+ * Drivers which use the mode setting helpers can use this function to
+ * force-restore the mode setting configuration e.g. on resume or when something
+ * else might have trampled over the hw state (like some overzealous old BIOSen
+ * tended to do).
+ *
+ * This helper doesn't provide a error return value since restoring the old
+ * config should never fail due to resource allocation issues since the driver
+ * has successfully set the restored configuration already. Hence this should
+ * boil down to the equivalent of a few dpms on calls, which also don't provide
+ * an error code.
+ *
+ * Drivers where simply restoring an old configuration again might fail (e.g.
+ * due to slight differences in allocating shared resources when the
+ * configuration is restored in a different order than when userspace set it up)
+ * need to use their own restore logic.
+ */
+void drm_helper_resume_force_mode(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
 	struct drm_encoder *encoder;
 	struct drm_crtc_helper_funcs *crtc_funcs;
-	int ret, encoder_dpms;
+	int encoder_dpms;
+	bool ret;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 
@@ -958,6 +984,7 @@
 		ret = drm_crtc_helper_set_mode(crtc, &crtc->mode,
 					       crtc->x, crtc->y, crtc->fb);
 
+		/* Restoring the old config should never fail! */
 		if (ret == false)
 			DRM_ERROR("failed to set mode on crtc %p\n", crtc);
 
@@ -980,12 +1007,28 @@
 						     drm_helper_choose_crtc_dpms(crtc));
 		}
 	}
+
 	/* disable the unused connectors while restoring the modesetting */
 	drm_helper_disable_unused_functions(dev);
-	return 0;
 }
 EXPORT_SYMBOL(drm_helper_resume_force_mode);
 
+/**
+ * drm_kms_helper_hotplug_event - fire off KMS hotplug events
+ * @dev: drm_device whose connector state changed
+ *
+ * This function fires off the uevent for userspace and also calls the
+ * output_poll_changed function, which is most commonly used to inform the fbdev
+ * emulation code and allow it to update the fbcon output configuration.
+ *
+ * Drivers should call this from their hotplug handling code when a change is
+ * detected. Note that this function does not do any output detection of its
+ * own, like drm_helper_hpd_irq_event() does - this is assumed to be done by the
+ * driver already.
+ *
+ * This function must be called from process context with no mode
+ * setting locks held.
+ */
 void drm_kms_helper_hotplug_event(struct drm_device *dev)
 {
 	/* send a uevent + call fbdev */
@@ -1054,6 +1097,16 @@
 		schedule_delayed_work(delayed_work, DRM_OUTPUT_POLL_PERIOD);
 }
 
+/**
+ * drm_kms_helper_poll_disable - disable output polling
+ * @dev: drm_device
+ *
+ * This function disables the output polling work.
+ *
+ * Drivers can call this helper from their device suspend implementation. It is
+ * not an error to call this even when output polling isn't enabled or arlready
+ * disabled.
+ */
 void drm_kms_helper_poll_disable(struct drm_device *dev)
 {
 	if (!dev->mode_config.poll_enabled)
@@ -1062,6 +1115,16 @@
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_disable);
 
+/**
+ * drm_kms_helper_poll_enable - re-enable output polling.
+ * @dev: drm_device
+ *
+ * This function re-enables the output polling work.
+ *
+ * Drivers can call this helper from their device resume implementation. It is
+ * an error to call this when the output polling support has not yet been set
+ * up.
+ */
 void drm_kms_helper_poll_enable(struct drm_device *dev)
 {
 	bool poll = false;
@@ -1081,6 +1144,25 @@
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_enable);
 
+/**
+ * drm_kms_helper_poll_init - initialize and enable output polling
+ * @dev: drm_device
+ *
+ * This function intializes and then also enables output polling support for
+ * @dev. Drivers which do not have reliable hotplug support in hardware can use
+ * this helper infrastructure to regularly poll such connectors for changes in
+ * their connection state.
+ *
+ * Drivers can control which connectors are polled by setting the
+ * DRM_CONNECTOR_POLL_CONNECT and DRM_CONNECTOR_POLL_DISCONNECT flags. On
+ * connectors where probing live outputs can result in visual distortion drivers
+ * should not set the DRM_CONNECTOR_POLL_DISCONNECT flag to avoid this.
+ * Connectors which have no flag or only DRM_CONNECTOR_POLL_HPD set are
+ * completely ignored by the polling logic.
+ *
+ * Note that a connector can be both polled and probed from the hotplug handler,
+ * in case the hotplug interrupt is known to be unreliable.
+ */
 void drm_kms_helper_poll_init(struct drm_device *dev)
 {
 	INIT_DELAYED_WORK(&dev->mode_config.output_poll_work, output_poll_execute);
@@ -1090,12 +1172,39 @@
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_init);
 
+/**
+ * drm_kms_helper_poll_fini - disable output polling and clean it up
+ * @dev: drm_device
+ */
 void drm_kms_helper_poll_fini(struct drm_device *dev)
 {
 	drm_kms_helper_poll_disable(dev);
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_fini);
 
+/**
+ * drm_helper_hpd_irq_event - hotplug processing
+ * @dev: drm_device
+ *
+ * Drivers can use this helper function to run a detect cycle on all connectors
+ * which have the DRM_CONNECTOR_POLL_HPD flag set in their &polled member. All
+ * other connectors are ignored, which is useful to avoid reprobing fixed
+ * panels.
+ *
+ * This helper function is useful for drivers which can't or don't track hotplug
+ * interrupts for each connector.
+ *
+ * Drivers which support hotplug interrupts for each connector individually and
+ * which have a more fine-grained detect logic should bypass this code and
+ * directly call drm_kms_helper_hotplug_event() in case the connector state
+ * changed.
+ *
+ * This function must be called from process context with no mode
+ * setting locks held.
+ *
+ * Note that a connector can be both polled and probed from the hotplug handler,
+ * in case the hotplug interrupt is known to be unreliable.
+ */
 bool drm_helper_hpd_irq_event(struct drm_device *dev)
 {
 	struct drm_connector *connector;
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
new file mode 100644
index 0000000..a2945ee
--- /dev/null
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright © 2006 Keith Packard
+ * Copyright © 2007-2008 Dave Airlie
+ * Copyright © 2007-2008 Intel Corporation
+ *   Jesse Barnes <jesse.barnes@intel.com>
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * 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.
+ */
+
+/*
+ * This header file contains mode setting related functions and definitions
+ * which are only used within the drm module as internal implementation details
+ * and are not exported to drivers.
+ */
+
+int drm_mode_object_get(struct drm_device *dev,
+			struct drm_mode_object *obj, uint32_t obj_type);
+void drm_mode_object_put(struct drm_device *dev,
+			 struct drm_mode_object *object);
+
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 345be03..ec651be 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -344,7 +344,7 @@
 
 	DRM_DEBUG("pid=%d, dev=0x%lx, auth=%d, %s\n",
 		  task_pid_nr(current),
-		  (long)old_encode_dev(file_priv->minor->device),
+		  (long)old_encode_dev(file_priv->minor->kdev->devt),
 		  file_priv->authenticated, ioctl->name);
 
 	/* Do not trust userspace, use our own definition */
@@ -402,7 +402,7 @@
 	if (!ioctl)
 		DRM_DEBUG("invalid ioctl: pid=%d, dev=0x%lx, auth=%d, cmd=0x%02x, nr=0x%02x\n",
 			  task_pid_nr(current),
-			  (long)old_encode_dev(file_priv->minor->device),
+			  (long)old_encode_dev(file_priv->minor->kdev->devt),
 			  file_priv->authenticated, cmd, nr);
 
 	if (kdata != stack_kdata)
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index f3cde90..d4e3f9d 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -1098,10 +1098,14 @@
 /**
  * Get EDID information via I2C.
  *
- * \param adapter : i2c device adaptor
- * \param buf     : EDID data buffer to be filled
- * \param len     : EDID data buffer length
- * \return 0 on success or -1 on failure.
+ * @adapter : i2c device adaptor
+ * @buf: EDID data buffer to be filled
+ * @block: 128 byte EDID block to start fetching from
+ * @len: EDID data buffer length to fetch
+ *
+ * Returns:
+ *
+ * 0 on success or -1 on failure.
  *
  * Try to fetch EDID information by calling i2c driver function.
  */
@@ -1243,9 +1247,11 @@
 
 /**
  * Probe DDC presence.
+ * @adapter: i2c adapter to probe
  *
- * \param adapter : i2c device adaptor
- * \return 1 on success
+ * Returns:
+ *
+ * 1 on success
  */
 bool
 drm_probe_ddc(struct i2c_adapter *adapter)
@@ -1586,8 +1592,10 @@
 
 /**
  * drm_mode_std - convert standard mode info (width, height, refresh) into mode
+ * @connector: connector of for the EDID block
+ * @edid: EDID block to scan
  * @t: standard timing params
- * @timing_level: standard timing level
+ * @revision: standard timing level
  *
  * Take the standard timing params (in this case width, aspect, and refresh)
  * and convert them into a real mode using CVT/GTF/DMT.
@@ -2132,6 +2140,7 @@
 
 /**
  * add_established_modes - get est. modes from EDID and add them
+ * @connector: connector of for the EDID block
  * @edid: EDID block to scan
  *
  * Each EDID block contains a bitmap of the supported "established modes" list
@@ -2194,6 +2203,7 @@
 
 /**
  * add_standard_modes - get std. modes from EDID and add them
+ * @connector: connector of for the EDID block
  * @edid: EDID block to scan
  *
  * Standard modes can be calculated using the appropriate standard (DMT,
@@ -3303,6 +3313,7 @@
 
 /**
  * drm_detect_monitor_audio - check monitor audio capability
+ * @edid: EDID block to scan
  *
  * Monitor should have CEA extension block.
  * If monitor has 'basic audio', but no CEA audio blocks, it's 'basic
@@ -3348,6 +3359,7 @@
 
 /**
  * drm_rgb_quant_range_selectable - is RGB quantization range selectable?
+ * @edid: EDID block to scan
  *
  * Check whether the monitor reports the RGB quantization range selection
  * as supported. The AVI infoframe can then be used to inform the monitor
@@ -3567,8 +3579,8 @@
 	struct drm_display_mode *mode;
 
 	list_for_each_entry(mode, &connector->probed_modes, head) {
-		if (drm_mode_width(mode)  == hpref &&
-		    drm_mode_height(mode) == vpref)
+		if (mode->hdisplay  == hpref &&
+		    mode->vdisplay == vpref)
 			mode->type |= DRM_MODE_TYPE_PREFERRED;
 	}
 }
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 89382dc..8787619 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1131,19 +1131,20 @@
 	return count;
 }
 
-static struct drm_display_mode *drm_has_preferred_mode(struct drm_fb_helper_connector *fb_connector, int width, int height)
+struct drm_display_mode *drm_has_preferred_mode(struct drm_fb_helper_connector *fb_connector, int width, int height)
 {
 	struct drm_display_mode *mode;
 
 	list_for_each_entry(mode, &fb_connector->connector->modes, head) {
-		if (drm_mode_width(mode) > width ||
-		    drm_mode_height(mode) > height)
+		if (mode->hdisplay > width ||
+		    mode->vdisplay > height)
 			continue;
 		if (mode->type & DRM_MODE_TYPE_PREFERRED)
 			return mode;
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(drm_has_preferred_mode);
 
 static bool drm_has_cmdline_mode(struct drm_fb_helper_connector *fb_connector)
 {
@@ -1152,7 +1153,7 @@
 	return cmdline_mode->specified;
 }
 
-static struct drm_display_mode *drm_pick_cmdline_mode(struct drm_fb_helper_connector *fb_helper_conn,
+struct drm_display_mode *drm_pick_cmdline_mode(struct drm_fb_helper_connector *fb_helper_conn,
 						      int width, int height)
 {
 	struct drm_cmdline_mode *cmdline_mode;
@@ -1192,6 +1193,7 @@
 	list_add(&mode->head, &fb_helper_conn->connector->modes);
 	return mode;
 }
+EXPORT_SYMBOL(drm_pick_cmdline_mode);
 
 static bool drm_connector_enabled(struct drm_connector *connector, bool strict)
 {
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 7f2af9a..9b02f12 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -39,12 +39,12 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
-/* from BKL pushdown: note that nothing else serializes idr_find() */
+/* from BKL pushdown */
 DEFINE_MUTEX(drm_global_mutex);
 EXPORT_SYMBOL(drm_global_mutex);
 
 static int drm_open_helper(struct inode *inode, struct file *filp,
-			   struct drm_device * dev);
+			   struct drm_minor *minor);
 
 static int drm_setup(struct drm_device * dev)
 {
@@ -79,38 +79,23 @@
  */
 int drm_open(struct inode *inode, struct file *filp)
 {
-	struct drm_device *dev = NULL;
-	int minor_id = iminor(inode);
+	struct drm_device *dev;
 	struct drm_minor *minor;
-	int retcode = 0;
+	int retcode;
 	int need_setup = 0;
-	struct address_space *old_mapping;
-	struct address_space *old_imapping;
 
-	minor = idr_find(&drm_minors_idr, minor_id);
-	if (!minor)
-		return -ENODEV;
+	minor = drm_minor_acquire(iminor(inode));
+	if (IS_ERR(minor))
+		return PTR_ERR(minor);
 
-	if (!(dev = minor->dev))
-		return -ENODEV;
-
-	if (drm_device_is_unplugged(dev))
-		return -ENODEV;
-
+	dev = minor->dev;
 	if (!dev->open_count++)
 		need_setup = 1;
-	mutex_lock(&dev->struct_mutex);
-	old_imapping = inode->i_mapping;
-	old_mapping = dev->dev_mapping;
-	if (old_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);
 
-	retcode = drm_open_helper(inode, filp, dev);
+	/* share address_space across all char-devs of a single device */
+	filp->f_mapping = dev->anon_inode->i_mapping;
+
+	retcode = drm_open_helper(inode, filp, minor);
 	if (retcode)
 		goto err_undo;
 	if (need_setup) {
@@ -121,13 +106,8 @@
 	return 0;
 
 err_undo:
-	mutex_lock(&dev->struct_mutex);
-	filp->f_mapping = old_imapping;
-	inode->i_mapping = old_imapping;
-	iput(container_of(dev->dev_mapping, struct inode, i_data));
-	dev->dev_mapping = old_mapping;
-	mutex_unlock(&dev->struct_mutex);
 	dev->open_count--;
+	drm_minor_release(minor);
 	return retcode;
 }
 EXPORT_SYMBOL(drm_open);
@@ -143,33 +123,30 @@
  */
 int drm_stub_open(struct inode *inode, struct file *filp)
 {
-	struct drm_device *dev = NULL;
+	struct drm_device *dev;
 	struct drm_minor *minor;
-	int minor_id = iminor(inode);
 	int err = -ENODEV;
 	const struct file_operations *new_fops;
 
 	DRM_DEBUG("\n");
 
 	mutex_lock(&drm_global_mutex);
-	minor = idr_find(&drm_minors_idr, minor_id);
-	if (!minor)
-		goto out;
+	minor = drm_minor_acquire(iminor(inode));
+	if (IS_ERR(minor))
+		goto out_unlock;
 
-	if (!(dev = minor->dev))
-		goto out;
-
-	if (drm_device_is_unplugged(dev))
-		goto out;
-
+	dev = minor->dev;
 	new_fops = fops_get(dev->driver->fops);
 	if (!new_fops)
-		goto out;
+		goto out_release;
 
 	replace_fops(filp, new_fops);
 	if (filp->f_op->open)
 		err = filp->f_op->open(inode, filp);
-out:
+
+out_release:
+	drm_minor_release(minor);
+out_unlock:
 	mutex_unlock(&drm_global_mutex);
 	return err;
 }
@@ -196,16 +173,16 @@
  *
  * \param inode device inode.
  * \param filp file pointer.
- * \param dev device.
+ * \param minor acquired minor-object.
  * \return zero on success or a negative number on failure.
  *
  * Creates and initializes a drm_file structure for the file private data in \p
  * filp and add it into the double linked list in \p dev.
  */
 static int drm_open_helper(struct inode *inode, struct file *filp,
-			   struct drm_device * dev)
+			   struct drm_minor *minor)
 {
-	int minor_id = iminor(inode);
+	struct drm_device *dev = minor->dev;
 	struct drm_file *priv;
 	int ret;
 
@@ -216,7 +193,7 @@
 	if (dev->switch_power_state != DRM_SWITCH_POWER_ON && dev->switch_power_state != DRM_SWITCH_POWER_DYNAMIC_OFF)
 		return -EINVAL;
 
-	DRM_DEBUG("pid = %d, minor = %d\n", task_pid_nr(current), minor_id);
+	DRM_DEBUG("pid = %d, minor = %d\n", task_pid_nr(current), minor->index);
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -226,11 +203,7 @@
 	priv->filp = filp;
 	priv->uid = current_euid();
 	priv->pid = get_pid(task_pid(current));
-	priv->minor = idr_find(&drm_minors_idr, minor_id);
-	if (!priv->minor) {
-		ret = -ENODEV;
-		goto out_put_pid;
-	}
+	priv->minor = minor;
 
 	/* for compatibility root is always authenticated */
 	priv->always_authenticated = capable(CAP_SYS_ADMIN);
@@ -336,7 +309,6 @@
 		drm_prime_destroy_file_private(&priv->prime);
 	if (dev->driver->driver_features & DRIVER_GEM)
 		drm_gem_release(dev, priv);
-out_put_pid:
 	put_pid(priv->pid);
 	kfree(priv);
 	filp->private_data = NULL;
@@ -434,7 +406,6 @@
 
 	drm_legacy_dma_takedown(dev);
 
-	dev->dev_mapping = NULL;
 	mutex_unlock(&dev->struct_mutex);
 
 	drm_legacy_dev_reinit(dev);
@@ -458,7 +429,8 @@
 int drm_release(struct inode *inode, struct file *filp)
 {
 	struct drm_file *file_priv = filp->private_data;
-	struct drm_device *dev = file_priv->minor->dev;
+	struct drm_minor *minor = file_priv->minor;
+	struct drm_device *dev = minor->dev;
 	int retcode = 0;
 
 	mutex_lock(&drm_global_mutex);
@@ -474,7 +446,7 @@
 
 	DRM_DEBUG("pid = %d, device = 0x%lx, open_count = %d\n",
 		  task_pid_nr(current),
-		  (long)old_encode_dev(file_priv->minor->device),
+		  (long)old_encode_dev(file_priv->minor->kdev->devt),
 		  dev->open_count);
 
 	/* Release any auth tokens that might point to this file_priv,
@@ -549,9 +521,6 @@
 		}
 	}
 
-	BUG_ON(dev->dev_mapping == NULL);
-	iput(container_of(dev->dev_mapping, struct inode, i_data));
-
 	/* drop the reference held my the file priv */
 	if (file_priv->master)
 		drm_master_put(&file_priv->master);
@@ -580,6 +549,8 @@
 	}
 	mutex_unlock(&drm_global_mutex);
 
+	drm_minor_release(minor);
+
 	return retcode;
 }
 EXPORT_SYMBOL(drm_release);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 5bbad87..9909bef 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -85,9 +85,9 @@
 #endif
 
 /**
- * Initialize the GEM device fields
+ * drm_gem_init - Initialize the GEM device fields
+ * @dev: drm_devic structure to initialize
  */
-
 int
 drm_gem_init(struct drm_device *dev)
 {
@@ -120,6 +120,11 @@
 }
 
 /**
+ * drm_gem_object_init - initialize an allocated shmem-backed GEM object
+ * @dev: drm_device the object should be initialized for
+ * @obj: drm_gem_object to initialize
+ * @size: object size
+ *
  * Initialize an already allocated GEM object of the specified size with
  * shmfs backing store.
  */
@@ -141,6 +146,11 @@
 EXPORT_SYMBOL(drm_gem_object_init);
 
 /**
+ * drm_gem_object_init - initialize an allocated private GEM object
+ * @dev: drm_device the object should be initialized for
+ * @obj: drm_gem_object to initialize
+ * @size: object size
+ *
  * Initialize an already allocated GEM object of the specified size with
  * no GEM provided backing store. Instead the caller is responsible for
  * backing the object and handling it.
@@ -176,6 +186,9 @@
 }
 
 /**
+ * drm_gem_object_free - release resources bound to userspace handles
+ * @obj: GEM object to clean up.
+ *
  * Called after the last handle to the object has been closed
  *
  * Removes any name for the object. Note that this must be
@@ -225,7 +238,12 @@
 }
 
 /**
- * Removes the mapping from handle to filp for this object.
+ * drm_gem_handle_delete - deletes the given file-private handle
+ * @filp: drm file-private structure to use for the handle look up
+ * @handle: userspace handle to delete
+ *
+ * Removes the GEM handle from the @filp lookup table and if this is the last
+ * handle also cleans up linked resources like GEM names.
  */
 int
 drm_gem_handle_delete(struct drm_file *filp, u32 handle)
@@ -270,6 +288,9 @@
 
 /**
  * drm_gem_dumb_destroy - dumb fb callback helper for gem based drivers
+ * @file: drm file-private structure to remove the dumb handle from
+ * @dev: corresponding drm_device
+ * @handle: the dumb handle to remove
  * 
  * This implements the ->dumb_destroy kms driver callback for drivers which use
  * gem to manage their backing storage.
@@ -284,6 +305,9 @@
 
 /**
  * drm_gem_handle_create_tail - internal functions to create a handle
+ * @file_priv: drm file-private structure to register the handle for
+ * @obj: object to register
+ * @handlep: pionter to return the created handle to the caller
  * 
  * This expects the dev->object_name_lock to be held already and will drop it
  * before returning. Used to avoid races in establishing new handles when
@@ -336,6 +360,11 @@
 }
 
 /**
+ * gem_handle_create - create a gem handle for an object
+ * @file_priv: drm file-private structure to register the handle for
+ * @obj: object to register
+ * @handlep: pionter to return the created handle to the caller
+ *
  * Create a handle for this object. This adds a handle reference
  * to the object, which includes a regular reference count. Callers
  * will likely want to dereference the object afterwards.
@@ -536,6 +565,11 @@
 EXPORT_SYMBOL(drm_gem_object_lookup);
 
 /**
+ * drm_gem_close_ioctl - implementation of the GEM_CLOSE ioctl
+ * @dev: drm_device
+ * @data: ioctl data
+ * @file_priv: drm file-private structure
+ *
  * Releases the handle to an mm object.
  */
 int
@@ -554,6 +588,11 @@
 }
 
 /**
+ * drm_gem_flink_ioctl - implementation of the GEM_FLINK ioctl
+ * @dev: drm_device
+ * @data: ioctl data
+ * @file_priv: drm file-private structure
+ *
  * Create a global name for an object, returning the name.
  *
  * Note that the name does not hold a reference; when the object
@@ -601,6 +640,11 @@
 }
 
 /**
+ * drm_gem_open - implementation of the GEM_OPEN ioctl
+ * @dev: drm_device
+ * @data: ioctl data
+ * @file_priv: drm file-private structure
+ *
  * Open an object using the global name, returning a handle and the size.
  *
  * This handle (of course) holds a reference to the object, so the object
@@ -640,6 +684,10 @@
 }
 
 /**
+ * gem_gem_open - initalizes GEM file-private structures at devnode open time
+ * @dev: drm_device which is being opened by userspace
+ * @file_private: drm file-private structure to set up
+ *
  * Called at device open time, sets up the structure for handling refcounting
  * of mm objects.
  */
@@ -650,7 +698,7 @@
 	spin_lock_init(&file_private->table_lock);
 }
 
-/**
+/*
  * Called at device close to release the file's
  * handle references on objects.
  */
@@ -674,6 +722,10 @@
 }
 
 /**
+ * drm_gem_release - release file-private GEM resources
+ * @dev: drm_device which is being closed by userspace
+ * @file_private: drm file-private structure to clean up
+ *
  * Called at close time when the filp is going away.
  *
  * Releases any remaining references on objects by this filp.
@@ -692,11 +744,16 @@
 	WARN_ON(obj->dma_buf);
 
 	if (obj->filp)
-	    fput(obj->filp);
+		fput(obj->filp);
+
+	drm_gem_free_mmap_offset(obj);
 }
 EXPORT_SYMBOL(drm_gem_object_release);
 
 /**
+ * drm_gem_object_free - free a GEM object
+ * @kref: kref of the object to free
+ *
  * Called after the last reference to the object has been lost.
  * Must be called holding struct_ mutex
  *
@@ -782,7 +839,7 @@
 	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_ops = dev->driver->gem_vm_ops;
 	vma->vm_private_data = obj;
-	vma->vm_page_prot =  pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 
 	/* Take a ref for this mapping of the object, so that the fault
 	 * handler can dereference the mmap offset's pointer to the object.
@@ -818,7 +875,7 @@
 	struct drm_device *dev = priv->minor->dev;
 	struct drm_gem_object *obj;
 	struct drm_vma_offset_node *node;
-	int ret = 0;
+	int ret;
 
 	if (drm_device_is_unplugged(dev))
 		return -ENODEV;
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 6b51bf9..2c07cb9 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -79,7 +79,6 @@
 		unsigned int size)
 {
 	struct drm_gem_cma_object *cma_obj;
-	struct sg_table *sgt = NULL;
 	int ret;
 
 	size = round_up(size, PAGE_SIZE);
@@ -97,23 +96,9 @@
 		goto error;
 	}
 
-	sgt = kzalloc(sizeof(*cma_obj->sgt), GFP_KERNEL);
-	if (sgt == NULL) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	ret = dma_get_sgtable(drm->dev, sgt, cma_obj->vaddr,
-			      cma_obj->paddr, size);
-	if (ret < 0)
-		goto error;
-
-	cma_obj->sgt = sgt;
-
 	return cma_obj;
 
 error:
-	kfree(sgt);
 	drm_gem_cma_free_object(&cma_obj->base);
 	return ERR_PTR(ret);
 }
@@ -175,10 +160,6 @@
 	if (cma_obj->vaddr) {
 		dma_free_writecombine(gem_obj->dev->dev, cma_obj->base.size,
 				      cma_obj->vaddr, cma_obj->paddr);
-		if (cma_obj->sgt) {
-			sg_free_table(cma_obj->sgt);
-			kfree(cma_obj->sgt);
-		}
 	} else if (gem_obj->import_attach) {
 		drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
 	}
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index af93cc5..a2d45b74 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -47,7 +47,44 @@
 #include <linux/seq_file.h>
 #include <linux/export.h>
 
-#define MM_UNUSED_TARGET 4
+/**
+ * DOC: Overview
+ *
+ * drm_mm provides a simple range allocator. The drivers are free to use the
+ * resource allocator from the linux core if it suits them, the upside of drm_mm
+ * is that it's in the DRM core. Which means that it's easier to extend for
+ * some of the crazier special purpose needs of gpus.
+ *
+ * The main data struct is &drm_mm, allocations are tracked in &drm_mm_node.
+ * Drivers are free to embed either of them into their own suitable
+ * datastructures. drm_mm itself will not do any allocations of its own, so if
+ * drivers choose not to embed nodes they need to still allocate them
+ * themselves.
+ *
+ * The range allocator also supports reservation of preallocated blocks. This is
+ * useful for taking over initial mode setting configurations from the firmware,
+ * where an object needs to be created which exactly matches the firmware's
+ * scanout target. As long as the range is still free it can be inserted anytime
+ * after the allocator is initialized, which helps with avoiding looped
+ * depencies in the driver load sequence.
+ *
+ * drm_mm maintains a stack of most recently freed holes, which of all
+ * simplistic datastructures seems to be a fairly decent approach to clustering
+ * allocations and avoiding too much fragmentation. This means free space
+ * searches are O(num_holes). Given that all the fancy features drm_mm supports
+ * something better would be fairly complex and since gfx thrashing is a fairly
+ * steep cliff not a real concern. Removing a node again is O(1).
+ *
+ * drm_mm supports a few features: Alignment and range restrictions can be
+ * supplied. Further more every &drm_mm_node has a color value (which is just an
+ * opaqua unsigned long) which in conjunction with a driver callback can be used
+ * to implement sophisticated placement restrictions. The i915 DRM driver uses
+ * this to implement guard pages between incompatible caching domains in the
+ * graphics TT.
+ *
+ * Finally iteration helpers to walk all nodes and all holes are provided as are
+ * some basic allocator dumpers for debugging.
+ */
 
 static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 						unsigned long size,
@@ -107,6 +144,20 @@
 	}
 }
 
+/**
+ * drm_mm_reserve_node - insert an pre-initialized node
+ * @mm: drm_mm allocator to insert @node into
+ * @node: drm_mm_node to insert
+ *
+ * This functions inserts an already set-up drm_mm_node into the allocator,
+ * meaning that start, size and color must be set by the caller. This is useful
+ * to initialize the allocator with preallocated objects which must be set-up
+ * before the range allocator can be set-up, e.g. when taking over a firmware
+ * framebuffer.
+ *
+ * Returns:
+ * 0 on success, -ENOSPC if there's no hole where @node is.
+ */
 int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 {
 	struct drm_mm_node *hole;
@@ -148,9 +199,18 @@
 EXPORT_SYMBOL(drm_mm_reserve_node);
 
 /**
- * Search for free space and insert a preallocated memory node. Returns
- * -ENOSPC if no suitable free area is available. The preallocated memory node
- * must be cleared.
+ * drm_mm_insert_node_generic - search for space and insert @node
+ * @mm: drm_mm to allocate from
+ * @node: preallocate node to insert
+ * @size: size of the allocation
+ * @alignment: alignment of the allocation
+ * @color: opaque tag value to use for this node
+ * @flags: flags to fine-tune the allocation
+ *
+ * The preallocated node must be cleared to 0.
+ *
+ * Returns:
+ * 0 on success, -ENOSPC if there's no suitable hole.
  */
 int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
 			       unsigned long size, unsigned alignment,
@@ -222,9 +282,20 @@
 }
 
 /**
- * Search for free space and insert a preallocated memory node. Returns
- * -ENOSPC if no suitable free area is available. This is for range
- * restricted allocations. The preallocated memory node must be cleared.
+ * drm_mm_insert_node_in_range_generic - ranged search for space and insert @node
+ * @mm: drm_mm to allocate from
+ * @node: preallocate node to insert
+ * @size: size of the allocation
+ * @alignment: alignment of the allocation
+ * @color: opaque tag value to use for this node
+ * @start: start of the allowed range for this node
+ * @end: end of the allowed range for this node
+ * @flags: flags to fine-tune the allocation
+ *
+ * The preallocated node must be cleared to 0.
+ *
+ * Returns:
+ * 0 on success, -ENOSPC if there's no suitable hole.
  */
 int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node,
 					unsigned long size, unsigned alignment, unsigned long color,
@@ -247,7 +318,12 @@
 EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic);
 
 /**
- * Remove a memory node from the allocator.
+ * drm_mm_remove_node - Remove a memory node from the allocator.
+ * @node: drm_mm_node to remove
+ *
+ * This just removes a node from its drm_mm allocator. The node does not need to
+ * be cleared again before it can be re-inserted into this or any other drm_mm
+ * allocator. It is a bug to call this function on a un-allocated node.
  */
 void drm_mm_remove_node(struct drm_mm_node *node)
 {
@@ -384,7 +460,13 @@
 }
 
 /**
- * Moves an allocation. To be used with embedded struct drm_mm_node.
+ * drm_mm_replace_node - move an allocation from @old to @new
+ * @old: drm_mm_node to remove from the allocator
+ * @new: drm_mm_node which should inherit @old's allocation
+ *
+ * This is useful for when drivers embed the drm_mm_node structure and hence
+ * can't move allocations by reassigning pointers. It's a combination of remove
+ * and insert with the guarantee that the allocation start will match.
  */
 void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new)
 {
@@ -402,12 +484,46 @@
 EXPORT_SYMBOL(drm_mm_replace_node);
 
 /**
- * Initializa lru scanning.
+ * DOC: lru scan roaster
+ *
+ * Very often GPUs need to have continuous allocations for a given object. When
+ * evicting objects to make space for a new one it is therefore not most
+ * efficient when we simply start to select all objects from the tail of an LRU
+ * until there's a suitable hole: Especially for big objects or nodes that
+ * otherwise have special allocation constraints there's a good chance we evict
+ * lots of (smaller) objects unecessarily.
+ *
+ * The DRM range allocator supports this use-case through the scanning
+ * interfaces. First a scan operation needs to be initialized with
+ * drm_mm_init_scan() or drm_mm_init_scan_with_range(). The the driver adds
+ * objects to the roaster (probably by walking an LRU list, but this can be
+ * freely implemented) until a suitable hole is found or there's no further
+ * evitable object.
+ *
+ * The the driver must walk through all objects again in exactly the reverse
+ * order to restore the allocator state. Note that while the allocator is used
+ * in the scan mode no other operation is allowed.
+ *
+ * Finally the driver evicts all objects selected in the scan. Adding and
+ * removing an object is O(1), and since freeing a node is also O(1) the overall
+ * complexity is O(scanned_objects). So like the free stack which needs to be
+ * walked before a scan operation even begins this is linear in the number of
+ * objects. It doesn't seem to hurt badly.
+ */
+
+/**
+ * drm_mm_init_scan - initialize lru scanning
+ * @mm: drm_mm to scan
+ * @size: size of the allocation
+ * @alignment: alignment of the allocation
+ * @color: opaque tag value to use for the allocation
  *
  * This simply sets up the scanning routines with the parameters for the desired
- * hole.
+ * hole. Note that there's no need to specify allocation flags, since they only
+ * change the place a node is allocated from within a suitable hole.
  *
- * Warning: As long as the scan list is non-empty, no other operations than
+ * Warning:
+ * As long as the scan list is non-empty, no other operations than
  * adding/removing nodes to/from the scan list are allowed.
  */
 void drm_mm_init_scan(struct drm_mm *mm,
@@ -427,12 +543,20 @@
 EXPORT_SYMBOL(drm_mm_init_scan);
 
 /**
- * Initializa lru scanning.
+ * drm_mm_init_scan - initialize range-restricted lru scanning
+ * @mm: drm_mm to scan
+ * @size: size of the allocation
+ * @alignment: alignment of the allocation
+ * @color: opaque tag value to use for the allocation
+ * @start: start of the allowed range for the allocation
+ * @end: end of the allowed range for the allocation
  *
  * This simply sets up the scanning routines with the parameters for the desired
- * hole. This version is for range-restricted scans.
+ * hole. Note that there's no need to specify allocation flags, since they only
+ * change the place a node is allocated from within a suitable hole.
  *
- * Warning: As long as the scan list is non-empty, no other operations than
+ * Warning:
+ * As long as the scan list is non-empty, no other operations than
  * adding/removing nodes to/from the scan list are allowed.
  */
 void drm_mm_init_scan_with_range(struct drm_mm *mm,
@@ -456,12 +580,16 @@
 EXPORT_SYMBOL(drm_mm_init_scan_with_range);
 
 /**
+ * drm_mm_scan_add_block - add a node to the scan list
+ * @node: drm_mm_node to add
+ *
  * Add a node to the scan list that might be freed to make space for the desired
  * hole.
  *
- * Returns non-zero, if a hole has been found, zero otherwise.
+ * Returns:
+ * True if a hole has been found, false otherwise.
  */
-int drm_mm_scan_add_block(struct drm_mm_node *node)
+bool drm_mm_scan_add_block(struct drm_mm_node *node)
 {
 	struct drm_mm *mm = node->mm;
 	struct drm_mm_node *prev_node;
@@ -501,15 +629,16 @@
 			    mm->scan_size, mm->scan_alignment)) {
 		mm->scan_hit_start = hole_start;
 		mm->scan_hit_end = hole_end;
-		return 1;
+		return true;
 	}
 
-	return 0;
+	return false;
 }
 EXPORT_SYMBOL(drm_mm_scan_add_block);
 
 /**
- * Remove a node from the scan list.
+ * drm_mm_scan_remove_block - remove a node from the scan list
+ * @node: drm_mm_node to remove
  *
  * Nodes _must_ be removed in the exact same order from the scan list as they
  * have been added, otherwise the internal state of the memory manager will be
@@ -519,10 +648,11 @@
  * immediately following drm_mm_search_free with !DRM_MM_SEARCH_BEST will then
  * return the just freed block (because its at the top of the free_stack list).
  *
- * Returns one if this block should be evicted, zero otherwise. Will always
- * return zero when no hole has been found.
+ * Returns:
+ * True if this block should be evicted, false otherwise. Will always
+ * return false when no hole has been found.
  */
-int drm_mm_scan_remove_block(struct drm_mm_node *node)
+bool drm_mm_scan_remove_block(struct drm_mm_node *node)
 {
 	struct drm_mm *mm = node->mm;
 	struct drm_mm_node *prev_node;
@@ -543,7 +673,15 @@
 }
 EXPORT_SYMBOL(drm_mm_scan_remove_block);
 
-int drm_mm_clean(struct drm_mm * mm)
+/**
+ * drm_mm_clean - checks whether an allocator is clean
+ * @mm: drm_mm allocator to check
+ *
+ * Returns:
+ * True if the allocator is completely free, false if there's still a node
+ * allocated in it.
+ */
+bool drm_mm_clean(struct drm_mm * mm)
 {
 	struct list_head *head = &mm->head_node.node_list;
 
@@ -551,6 +689,14 @@
 }
 EXPORT_SYMBOL(drm_mm_clean);
 
+/**
+ * drm_mm_init - initialize a drm-mm allocator
+ * @mm: the drm_mm structure to initialize
+ * @start: start of the range managed by @mm
+ * @size: end of the range managed by @mm
+ *
+ * Note that @mm must be cleared to 0 before calling this function.
+ */
 void drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size)
 {
 	INIT_LIST_HEAD(&mm->hole_stack);
@@ -572,6 +718,13 @@
 }
 EXPORT_SYMBOL(drm_mm_init);
 
+/**
+ * drm_mm_takedown - clean up a drm_mm allocator
+ * @mm: drm_mm allocator to clean up
+ *
+ * Note that it is a bug to call this function on an allocator which is not
+ * clean.
+ */
 void drm_mm_takedown(struct drm_mm * mm)
 {
 	WARN(!list_empty(&mm->head_node.node_list),
@@ -597,6 +750,11 @@
 	return 0;
 }
 
+/**
+ * drm_mm_debug_table - dump allocator state to dmesg
+ * @mm: drm_mm allocator to dump
+ * @prefix: prefix to use for dumping to dmesg
+ */
 void drm_mm_debug_table(struct drm_mm *mm, const char *prefix)
 {
 	struct drm_mm_node *entry;
@@ -635,6 +793,11 @@
 	return 0;
 }
 
+/**
+ * drm_mm_dump_table - dump allocator state to a seq_file
+ * @m: seq_file to dump to
+ * @mm: drm_mm allocator to dump
+ */
 int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm)
 {
 	struct drm_mm_node *entry;
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index b073315..8b41057 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -37,15 +37,14 @@
 #include <drm/drm_crtc.h>
 #include <video/of_videomode.h>
 #include <video/videomode.h>
+#include <drm/drm_modes.h>
+
+#include "drm_crtc_internal.h"
 
 /**
- * drm_mode_debug_printmodeline - debug print a mode
- * @dev: DRM device
+ * drm_mode_debug_printmodeline - print a mode to dmesg
  * @mode: mode to print
  *
- * LOCKING:
- * None.
- *
  * Describe @mode using DRM_DEBUG.
  */
 void drm_mode_debug_printmodeline(const struct drm_display_mode *mode)
@@ -61,18 +60,77 @@
 EXPORT_SYMBOL(drm_mode_debug_printmodeline);
 
 /**
- * drm_cvt_mode -create a modeline based on CVT algorithm
+ * drm_mode_create - create a new display mode
  * @dev: DRM device
+ *
+ * Create a new, cleared drm_display_mode with kzalloc, allocate an ID for it
+ * and return it.
+ *
+ * Returns:
+ * Pointer to new mode on success, NULL on error.
+ */
+struct drm_display_mode *drm_mode_create(struct drm_device *dev)
+{
+	struct drm_display_mode *nmode;
+
+	nmode = kzalloc(sizeof(struct drm_display_mode), GFP_KERNEL);
+	if (!nmode)
+		return NULL;
+
+	if (drm_mode_object_get(dev, &nmode->base, DRM_MODE_OBJECT_MODE)) {
+		kfree(nmode);
+		return NULL;
+	}
+
+	return nmode;
+}
+EXPORT_SYMBOL(drm_mode_create);
+
+/**
+ * drm_mode_destroy - remove a mode
+ * @dev: DRM device
+ * @mode: mode to remove
+ *
+ * Release @mode's unique ID, then free it @mode structure itself using kfree.
+ */
+void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode)
+{
+	if (!mode)
+		return;
+
+	drm_mode_object_put(dev, &mode->base);
+
+	kfree(mode);
+}
+EXPORT_SYMBOL(drm_mode_destroy);
+
+/**
+ * drm_mode_probed_add - add a mode to a connector's probed_mode list
+ * @connector: connector the new mode
+ * @mode: mode data
+ *
+ * Add @mode to @connector's probed_mode list for later use. This list should
+ * then in a second step get filtered and all the modes actually supported by
+ * the hardware moved to the @connector's modes list.
+ */
+void drm_mode_probed_add(struct drm_connector *connector,
+			 struct drm_display_mode *mode)
+{
+	WARN_ON(!mutex_is_locked(&connector->dev->mode_config.mutex));
+
+	list_add_tail(&mode->head, &connector->probed_modes);
+}
+EXPORT_SYMBOL(drm_mode_probed_add);
+
+/**
+ * drm_cvt_mode -create a modeline based on the CVT algorithm
+ * @dev: drm device
  * @hdisplay: hdisplay size
  * @vdisplay: vdisplay size
- * @vrefresh  : vrefresh rate
- * @reduced : Whether the GTF calculation is simplified
- * @interlaced:Whether the interlace is supported
- *
- * LOCKING:
- * none.
- *
- * return the modeline based on CVT algorithm
+ * @vrefresh: vrefresh rate
+ * @reduced: whether to use reduced blanking
+ * @interlaced: whether to compute an interlaced mode
+ * @margins: whether to add margins (borders)
  *
  * This function is called to generate the modeline based on CVT algorithm
  * according to the hdisplay, vdisplay, vrefresh.
@@ -82,12 +140,17 @@
  *
  * And it is copied from xf86CVTmode in xserver/hw/xfree86/modes/xf86cvt.c.
  * What I have done is to translate it by using integer calculation.
+ *
+ * Returns:
+ * The modeline based on the CVT algorithm stored in a drm_display_mode object.
+ * The display mode object is allocated with drm_mode_create(). Returns NULL
+ * when no mode could be allocated.
  */
-#define HV_FACTOR			1000
 struct drm_display_mode *drm_cvt_mode(struct drm_device *dev, int hdisplay,
 				      int vdisplay, int vrefresh,
 				      bool reduced, bool interlaced, bool margins)
 {
+#define HV_FACTOR			1000
 	/* 1) top/bottom margin size (% of height) - default: 1.8, */
 #define	CVT_MARGIN_PERCENTAGE		18
 	/* 2) character cell horizontal granularity (pixels) - default 8 */
@@ -281,23 +344,25 @@
 EXPORT_SYMBOL(drm_cvt_mode);
 
 /**
- * drm_gtf_mode_complex - create the modeline based on full GTF algorithm
- *
- * @dev		:drm device
- * @hdisplay	:hdisplay size
- * @vdisplay	:vdisplay size
- * @vrefresh	:vrefresh rate.
- * @interlaced	:whether the interlace is supported
- * @margins	:desired margin size
- * @GTF_[MCKJ]  :extended GTF formula parameters
- *
- * LOCKING.
- * none.
- *
- * return the modeline based on full GTF algorithm.
+ * drm_gtf_mode_complex - create the modeline based on the full GTF algorithm
+ * @dev: drm device
+ * @hdisplay: hdisplay size
+ * @vdisplay: vdisplay size
+ * @vrefresh: vrefresh rate.
+ * @interlaced: whether to compute an interlaced mode
+ * @margins: desired margin (borders) size
+ * @GTF_M: extended GTF formula parameters
+ * @GTF_2C: extended GTF formula parameters
+ * @GTF_K: extended GTF formula parameters
+ * @GTF_2J: extended GTF formula parameters
  *
  * GTF feature blocks specify C and J in multiples of 0.5, so we pass them
  * in here multiplied by two.  For a C of 40, pass in 80.
+ *
+ * Returns:
+ * The modeline based on the full GTF algorithm stored in a drm_display_mode object.
+ * The display mode object is allocated with drm_mode_create(). Returns NULL
+ * when no mode could be allocated.
  */
 struct drm_display_mode *
 drm_gtf_mode_complex(struct drm_device *dev, int hdisplay, int vdisplay,
@@ -467,17 +532,13 @@
 EXPORT_SYMBOL(drm_gtf_mode_complex);
 
 /**
- * drm_gtf_mode - create the modeline based on GTF algorithm
- *
- * @dev		:drm device
- * @hdisplay	:hdisplay size
- * @vdisplay	:vdisplay size
- * @vrefresh	:vrefresh rate.
- * @interlaced	:whether the interlace is supported
- * @margins	:whether the margin is supported
- *
- * LOCKING.
- * none.
+ * drm_gtf_mode - create the modeline based on the GTF algorithm
+ * @dev: drm device
+ * @hdisplay: hdisplay size
+ * @vdisplay: vdisplay size
+ * @vrefresh: vrefresh rate.
+ * @interlaced: whether to compute an interlaced mode
+ * @margins: desired margin (borders) size
  *
  * return the modeline based on GTF algorithm
  *
@@ -496,19 +557,32 @@
  * C = 40
  * K = 128
  * J = 20
+ *
+ * Returns:
+ * The modeline based on the GTF algorithm stored in a drm_display_mode object.
+ * The display mode object is allocated with drm_mode_create(). Returns NULL
+ * when no mode could be allocated.
  */
 struct drm_display_mode *
 drm_gtf_mode(struct drm_device *dev, int hdisplay, int vdisplay, int vrefresh,
-	     bool lace, int margins)
+	     bool interlaced, int margins)
 {
-	return drm_gtf_mode_complex(dev, hdisplay, vdisplay, vrefresh, lace,
-				    margins, 600, 40 * 2, 128, 20 * 2);
+	return drm_gtf_mode_complex(dev, hdisplay, vdisplay, vrefresh,
+				    interlaced, margins,
+				    600, 40 * 2, 128, 20 * 2);
 }
 EXPORT_SYMBOL(drm_gtf_mode);
 
 #ifdef CONFIG_VIDEOMODE_HELPERS
-int drm_display_mode_from_videomode(const struct videomode *vm,
-				    struct drm_display_mode *dmode)
+/**
+ * drm_display_mode_from_videomode - fill in @dmode using @vm,
+ * @vm: videomode structure to use as source
+ * @dmode: drm_display_mode structure to use as destination
+ *
+ * Fills out @dmode using the display mode specified in @vm.
+ */
+void drm_display_mode_from_videomode(const struct videomode *vm,
+				     struct drm_display_mode *dmode)
 {
 	dmode->hdisplay = vm->hactive;
 	dmode->hsync_start = dmode->hdisplay + vm->hfront_porch;
@@ -538,8 +612,6 @@
 	if (vm->flags & DISPLAY_FLAGS_DOUBLECLK)
 		dmode->flags |= DRM_MODE_FLAG_DBLCLK;
 	drm_mode_set_name(dmode);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(drm_display_mode_from_videomode);
 
@@ -553,6 +625,9 @@
  * This function is expensive and should only be used, if only one mode is to be
  * read from DT. To get multiple modes start with of_get_display_timings and
  * work with that instead.
+ *
+ * Returns:
+ * 0 on success, a negative errno code when no of videomode node was found.
  */
 int of_get_drm_display_mode(struct device_node *np,
 			    struct drm_display_mode *dmode, int index)
@@ -580,10 +655,8 @@
  * drm_mode_set_name - set the name on a mode
  * @mode: name will be set in this mode
  *
- * LOCKING:
- * None.
- *
- * Set the name of @mode to a standard format.
+ * Set the name of @mode to a standard format which is <hdisplay>x<vdisplay>
+ * with an optional 'i' suffix for interlaced modes.
  */
 void drm_mode_set_name(struct drm_display_mode *mode)
 {
@@ -595,54 +668,12 @@
 }
 EXPORT_SYMBOL(drm_mode_set_name);
 
-/**
- * drm_mode_width - get the width of a mode
- * @mode: mode
- *
- * LOCKING:
- * None.
- *
- * Return @mode's width (hdisplay) value.
- *
- * FIXME: is this needed?
- *
- * RETURNS:
- * @mode->hdisplay
- */
-int drm_mode_width(const struct drm_display_mode *mode)
-{
-	return mode->hdisplay;
-
-}
-EXPORT_SYMBOL(drm_mode_width);
-
-/**
- * drm_mode_height - get the height of a mode
- * @mode: mode
- *
- * LOCKING:
- * None.
- *
- * Return @mode's height (vdisplay) value.
- *
- * FIXME: is this needed?
- *
- * RETURNS:
- * @mode->vdisplay
- */
-int drm_mode_height(const struct drm_display_mode *mode)
-{
-	return mode->vdisplay;
-}
-EXPORT_SYMBOL(drm_mode_height);
-
 /** drm_mode_hsync - get the hsync of a mode
  * @mode: mode
  *
- * LOCKING:
- * None.
- *
- * Return @modes's hsync rate in kHz, rounded to the nearest int.
+ * Returns:
+ * @modes's hsync rate in kHz, rounded to the nearest integer. Calculates the
+ * value first if it is not yet set.
  */
 int drm_mode_hsync(const struct drm_display_mode *mode)
 {
@@ -666,17 +697,9 @@
  * drm_mode_vrefresh - get the vrefresh of a mode
  * @mode: mode
  *
- * LOCKING:
- * None.
- *
- * Return @mode's vrefresh rate in Hz or calculate it if necessary.
- *
- * FIXME: why is this needed?  shouldn't vrefresh be set already?
- *
- * RETURNS:
- * Vertical refresh rate. It will be the result of actual value plus 0.5.
- * If it is 70.288, it will return 70Hz.
- * If it is 59.6, it will return 60Hz.
+ * Returns:
+ * @modes's vrefresh rate in Hz, rounded to the nearest integer. Calculates the
+ * value first if it is not yet set.
  */
 int drm_mode_vrefresh(const struct drm_display_mode *mode)
 {
@@ -705,14 +728,11 @@
 EXPORT_SYMBOL(drm_mode_vrefresh);
 
 /**
- * drm_mode_set_crtcinfo - set CRTC modesetting parameters
+ * drm_mode_set_crtcinfo - set CRTC modesetting timing parameters
  * @p: mode
  * @adjust_flags: a combination of adjustment flags
  *
- * LOCKING:
- * None.
- *
- * Setup the CRTC modesetting parameters for @p, adjusting if necessary.
+ * Setup the CRTC modesetting timing parameters for @p, adjusting if necessary.
  *
  * - The CRTC_INTERLACE_HALVE_V flag can be used to halve vertical timings of
  *   interlaced modes.
@@ -780,15 +800,11 @@
 }
 EXPORT_SYMBOL(drm_mode_set_crtcinfo);
 
-
 /**
  * drm_mode_copy - copy the mode
  * @dst: mode to overwrite
  * @src: mode to copy
  *
- * LOCKING:
- * None.
- *
  * Copy an existing mode into another mode, preserving the object id and
  * list head of the destination mode.
  */
@@ -805,13 +821,14 @@
 
 /**
  * drm_mode_duplicate - allocate and duplicate an existing mode
- * @m: mode to duplicate
- *
- * LOCKING:
- * None.
+ * @dev: drm_device to allocate the duplicated mode for
+ * @mode: mode to duplicate
  *
  * Just allocate a new mode, copy the existing mode into it, and return
  * a pointer to it.  Used to create new instances of established modes.
+ *
+ * Returns:
+ * Pointer to duplicated mode on success, NULL on error.
  */
 struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev,
 					    const struct drm_display_mode *mode)
@@ -833,12 +850,9 @@
  * @mode1: first mode
  * @mode2: second mode
  *
- * LOCKING:
- * None.
- *
  * Check to see if @mode1 and @mode2 are equivalent.
  *
- * RETURNS:
+ * Returns:
  * True if the modes are equal, false otherwise.
  */
 bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2)
@@ -864,13 +878,10 @@
  * @mode1: first mode
  * @mode2: second mode
  *
- * LOCKING:
- * None.
- *
  * Check to see if @mode1 and @mode2 are equivalent, but
  * don't check the pixel clocks nor the stereo layout.
  *
- * RETURNS:
+ * Returns:
  * True if the modes are equal, false otherwise.
  */
 bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1,
@@ -900,25 +911,19 @@
  * @mode_list: list of modes to check
  * @maxX: maximum width
  * @maxY: maximum height
- * @maxPitch: max pitch
  *
- * LOCKING:
- * Caller must hold a lock protecting @mode_list.
- *
- * The DRM device (@dev) has size and pitch limits.  Here we validate the
- * modes we probed for @dev against those limits and set their status as
- * necessary.
+ * This function is a helper which can be used to validate modes against size
+ * limitations of the DRM device/connector. If a mode is too big its status
+ * memeber is updated with the appropriate validation failure code. The list
+ * itself is not changed.
  */
 void drm_mode_validate_size(struct drm_device *dev,
 			    struct list_head *mode_list,
-			    int maxX, int maxY, int maxPitch)
+			    int maxX, int maxY)
 {
 	struct drm_display_mode *mode;
 
 	list_for_each_entry(mode, mode_list, head) {
-		if (maxPitch > 0 && mode->hdisplay > maxPitch)
-			mode->status = MODE_BAD_WIDTH;
-
 		if (maxX > 0 && mode->hdisplay > maxX)
 			mode->status = MODE_VIRTUAL_X;
 
@@ -934,12 +939,10 @@
  * @mode_list: list of modes to check
  * @verbose: be verbose about it
  *
- * LOCKING:
- * Caller must hold a lock protecting @mode_list.
- *
- * Once mode list generation is complete, a caller can use this routine to
- * remove invalid modes from a mode list.  If any of the modes have a
- * status other than %MODE_OK, they are removed from @mode_list and freed.
+ * This helper function can be used to prune a display mode list after
+ * validation has been completed. All modes who's status is not MODE_OK will be
+ * removed from the list, and if @verbose the status code and mode name is also
+ * printed to dmesg.
  */
 void drm_mode_prune_invalid(struct drm_device *dev,
 			    struct list_head *mode_list, bool verbose)
@@ -966,13 +969,10 @@
  * @lh_a: list_head for first mode
  * @lh_b: list_head for second mode
  *
- * LOCKING:
- * None.
- *
  * Compare two modes, given by @lh_a and @lh_b, returning a value indicating
  * which is better.
  *
- * RETURNS:
+ * Returns:
  * Negative if @lh_a is better than @lh_b, zero if they're equivalent, or
  * positive if @lh_b is better than @lh_a.
  */
@@ -1000,12 +1000,9 @@
 
 /**
  * drm_mode_sort - sort mode list
- * @mode_list: list to sort
+ * @mode_list: list of drm_display_mode structures to sort
  *
- * LOCKING:
- * Caller must hold a lock protecting @mode_list.
- *
- * Sort @mode_list by favorability, putting good modes first.
+ * Sort @mode_list by favorability, moving good modes to the head of the list.
  */
 void drm_mode_sort(struct list_head *mode_list)
 {
@@ -1017,13 +1014,12 @@
  * drm_mode_connector_list_update - update the mode list for the connector
  * @connector: the connector to update
  *
- * LOCKING:
- * Caller must hold a lock protecting @mode_list.
- *
  * This moves the modes from the @connector probed_modes list
  * to the actual mode list. It compares the probed mode against the current
- * list and only adds different modes. All modes unverified after this point
- * will be removed by the prune invalid modes.
+ * list and only adds different/new modes.
+ *
+ * This is just a helper functions doesn't validate any modes itself and also
+ * doesn't prune any invalid modes. Callers need to do that themselves.
  */
 void drm_mode_connector_list_update(struct drm_connector *connector)
 {
@@ -1031,6 +1027,8 @@
 	struct drm_display_mode *pmode, *pt;
 	int found_it;
 
+	WARN_ON(!mutex_is_locked(&connector->dev->mode_config.mutex));
+
 	list_for_each_entry_safe(pmode, pt, &connector->probed_modes,
 				 head) {
 		found_it = 0;
@@ -1056,17 +1054,25 @@
 EXPORT_SYMBOL(drm_mode_connector_list_update);
 
 /**
- * drm_mode_parse_command_line_for_connector - parse command line for connector
- * @mode_option - per connector mode option
- * @connector - connector to parse line for
+ * drm_mode_parse_command_line_for_connector - parse command line modeline for connector
+ * @mode_option: optional per connector mode option
+ * @connector: connector to parse modeline for
+ * @mode: preallocated drm_cmdline_mode structure to fill out
  *
- * This parses the connector specific then generic command lines for
- * modes and options to configure the connector.
+ * This parses @mode_option command line modeline for modes and options to
+ * configure the connector. If @mode_option is NULL the default command line
+ * modeline in fb_mode_option will be parsed instead.
  *
- * This uses the same parameters as the fb modedb.c, except for extra
+ * This uses the same parameters as the fb modedb.c, except for an extra
+ * force-enable, force-enable-digital and force-disable bit at the end:
+ *
  *	<xres>x<yres>[M][R][-<bpp>][@<refresh>][i][m][eDd]
  *
- * enable/enable Digital/disable bit at the end
+ * The intermediate drm_cmdline_mode structure is required to store additional
+ * options from the command line modline like the force-enabel/disable flag.
+ *
+ * Returns:
+ * True if a valid modeline has been parsed, false otherwise.
  */
 bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 					       struct drm_connector *connector,
@@ -1219,6 +1225,14 @@
 }
 EXPORT_SYMBOL(drm_mode_parse_command_line_for_connector);
 
+/**
+ * drm_mode_create_from_cmdline_mode - convert a command line modeline into a DRM display mode
+ * @dev: DRM device to create the new mode for
+ * @cmd: input command line modeline
+ *
+ * Returns:
+ * Pointer to converted mode on success, NULL on error.
+ */
 struct drm_display_mode *
 drm_mode_create_from_cmdline_mode(struct drm_device *dev,
 				  struct drm_cmdline_mode *cmd)
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index f7af69b..9c696a5 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -351,7 +351,7 @@
 	drm_pci_agp_destroy(dev);
 	pci_disable_device(pdev);
 err_free:
-	drm_dev_free(dev);
+	drm_dev_unref(dev);
 	return ret;
 }
 EXPORT_SYMBOL(drm_get_pci_dev);
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index 21fc820..319ff53 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -64,7 +64,7 @@
 	return 0;
 
 err_free:
-	drm_dev_free(dev);
+	drm_dev_unref(dev);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 56805c3..f1437b6 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -68,7 +68,8 @@
 	enum dma_data_direction dir;
 };
 
-static int drm_prime_add_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t handle)
+static int drm_prime_add_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				    struct dma_buf *dma_buf, uint32_t handle)
 {
 	struct drm_prime_member *member;
 
@@ -174,7 +175,7 @@
 }
 
 static struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
-		enum dma_data_direction dir)
+					    enum dma_data_direction dir)
 {
 	struct drm_prime_attachment *prime_attach = attach->priv;
 	struct drm_gem_object *obj = attach->dmabuf->priv;
@@ -211,11 +212,19 @@
 }
 
 static void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
-		struct sg_table *sgt, enum dma_data_direction dir)
+				  struct sg_table *sgt,
+				  enum dma_data_direction dir)
 {
 	/* nothing to be done here */
 }
 
+/**
+ * drm_gem_dmabuf_release - dma_buf release implementation for GEM
+ * @dma_buf: buffer to be released
+ *
+ * Generic release function for dma_bufs exported as PRIME buffers. GEM drivers
+ * must use this in their dma_buf ops structure as the release callback.
+ */
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
@@ -242,30 +251,30 @@
 }
 
 static void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-		unsigned long page_num)
+					unsigned long page_num)
 {
 	return NULL;
 }
 
 static void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-		unsigned long page_num, void *addr)
+					 unsigned long page_num, void *addr)
 {
 
 }
 static void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf,
-		unsigned long page_num)
+				 unsigned long page_num)
 {
 	return NULL;
 }
 
 static void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf,
-		unsigned long page_num, void *addr)
+				  unsigned long page_num, void *addr)
 {
 
 }
 
 static int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf,
-		struct vm_area_struct *vma)
+			       struct vm_area_struct *vma)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
@@ -315,6 +324,15 @@
  *    driver's scatter/gather table
  */
 
+/**
+ * drm_gem_prime_export - helper library implemention of the export callback
+ * @dev: drm_device to export from
+ * @obj: GEM object to export
+ * @flags: flags like DRM_CLOEXEC
+ *
+ * This is the implementation of the gem_prime_export functions for GEM drivers
+ * using the PRIME helpers.
+ */
 struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
 				     struct drm_gem_object *obj, int flags)
 {
@@ -355,9 +373,23 @@
 	return dmabuf;
 }
 
+/**
+ * drm_gem_prime_handle_to_fd - PRIME export function for GEM drivers
+ * @dev: dev to export the buffer from
+ * @file_priv: drm file-private structure
+ * @handle: buffer handle to export
+ * @flags: flags like DRM_CLOEXEC
+ * @prime_fd: pointer to storage for the fd id of the create dma-buf
+ *
+ * This is the PRIME export function which must be used mandatorily by GEM
+ * drivers to ensure correct lifetime management of the underlying GEM object.
+ * The actual exporting from GEM object to a dma-buf is done through the
+ * gem_prime_export driver callback.
+ */
 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_file *file_priv, uint32_t handle,
+			       uint32_t flags,
+			       int *prime_fd)
 {
 	struct drm_gem_object *obj;
 	int ret = 0;
@@ -441,6 +473,14 @@
 }
 EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
 
+/**
+ * drm_gem_prime_import - helper library implemention of the import callback
+ * @dev: drm_device to import into
+ * @dma_buf: dma-buf object to import
+ *
+ * This is the implementation of the gem_prime_import functions for GEM drivers
+ * using the PRIME helpers.
+ */
 struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev,
 					    struct dma_buf *dma_buf)
 {
@@ -496,8 +536,21 @@
 }
 EXPORT_SYMBOL(drm_gem_prime_import);
 
+/**
+ * drm_gem_prime_fd_to_handle - PRIME import function for GEM drivers
+ * @dev: dev to export the buffer from
+ * @file_priv: drm file-private structure
+ * @prime_fd: fd id of the dma-buf which should be imported
+ * @handle: pointer to storage for the handle of the imported buffer object
+ *
+ * This is the PRIME import function which must be used mandatorily by GEM
+ * drivers to ensure correct lifetime management of the underlying GEM object.
+ * The actual importing of GEM object from the dma-buf is done through the
+ * gem_import_export driver callback.
+ */
 int drm_gem_prime_fd_to_handle(struct drm_device *dev,
-		struct drm_file *file_priv, int prime_fd, uint32_t *handle)
+			       struct drm_file *file_priv, int prime_fd,
+			       uint32_t *handle)
 {
 	struct dma_buf *dma_buf;
 	struct drm_gem_object *obj;
@@ -598,12 +651,14 @@
 			args->fd, &args->handle);
 }
 
-/*
- * drm_prime_pages_to_sg
+/**
+ * drm_prime_pages_to_sg - converts a page array into an sg list
+ * @pages: pointer to the array of page pointers to convert
+ * @nr_pages: length of the page vector
  *
- * this helper creates an sg table object from a set of pages
+ * 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
+ * importers address space for use with dma_buf itself.
  */
 struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages)
 {
@@ -628,9 +683,16 @@
 }
 EXPORT_SYMBOL(drm_prime_pages_to_sg);
 
-/* export an sg table into an array of pages and addresses
-   this is currently required by the TTM driver in order to do correct fault
-   handling */
+/**
+ * drm_prime_sg_to_page_addr_arrays - convert an sg table into a page array
+ * @sgt: scatter-gather table to convert
+ * @pages: array of page pointers to store the page array in
+ * @addrs: optional array to store the dma bus address of each page
+ * @max_pages: size of both the passed-in arrays
+ *
+ * Exports an sg table into an array of pages and addresses. This is currently
+ * required by the TTM driver in order to do correct fault handling.
+ */
 int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages,
 				     dma_addr_t *addrs, int max_pages)
 {
@@ -663,7 +725,15 @@
 	return 0;
 }
 EXPORT_SYMBOL(drm_prime_sg_to_page_addr_arrays);
-/* helper function to cleanup a GEM/prime object */
+
+/**
+ * drm_prime_gem_destroy - helper to clean up a PRIME-imported GEM object
+ * @obj: GEM object which was created from a dma-buf
+ * @sg: the sg-table which was pinned at import time
+ *
+ * This is the cleanup functions which GEM drivers need to call when they use
+ * @drm_gem_prime_import to import dma-bufs.
+ */
 void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg)
 {
 	struct dma_buf_attachment *attach;
@@ -683,11 +753,9 @@
 	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)
 {
 	/* by now drm_gem_release should've made sure the list is empty */
 	WARN_ON(!list_empty(&prime_fpriv->head));
 }
-EXPORT_SYMBOL(drm_prime_destroy_file_private);
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 98a33c580..dc2c609 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -31,8 +31,10 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/mount.h>
 #include <linux/slab.h>
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
@@ -70,6 +72,7 @@
 module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
 module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 
+static DEFINE_SPINLOCK(drm_minor_lock);
 struct idr drm_minors_idr;
 
 struct class *drm_class;
@@ -117,26 +120,6 @@
 }
 EXPORT_SYMBOL(drm_ut_debug_printk);
 
-static int drm_minor_get_id(struct drm_device *dev, int type)
-{
-	int ret;
-	int base = 0, limit = 63;
-
-	if (type == DRM_MINOR_CONTROL) {
-		base += 64;
-		limit = base + 63;
-	} else if (type == DRM_MINOR_RENDER) {
-		base += 128;
-		limit = base + 63;
-	}
-
-	mutex_lock(&dev->struct_mutex);
-	ret = idr_alloc(&drm_minors_idr, NULL, base, limit, GFP_KERNEL);
-	mutex_unlock(&dev->struct_mutex);
-
-	return ret == -ENOSPC ? -EINVAL : ret;
-}
-
 struct drm_master *drm_master_create(struct drm_minor *minor)
 {
 	struct drm_master *master;
@@ -260,119 +243,183 @@
 	return 0;
 }
 
-/**
- * drm_get_minor - Allocate and register new DRM minor
- * @dev: DRM device
- * @minor: Pointer to where new minor is stored
- * @type: Type of minor
+/*
+ * DRM Minors
+ * A DRM device can provide several char-dev interfaces on the DRM-Major. Each
+ * of them is represented by a drm_minor object. Depending on the capabilities
+ * of the device-driver, different interfaces are registered.
  *
- * Allocate a new minor of the given type and register it. A pointer to the new
- * minor is returned in @minor.
- * Caller must hold the global DRM mutex.
- *
- * RETURNS:
- * 0 on success, negative error code on failure.
+ * Minors can be accessed via dev->$minor_name. This pointer is either
+ * NULL or a valid drm_minor pointer and stays valid as long as the device is
+ * valid. This means, DRM minors have the same life-time as the underlying
+ * device. However, this doesn't mean that the minor is active. Minors are
+ * registered and unregistered dynamically according to device-state.
  */
-static int drm_get_minor(struct drm_device *dev, struct drm_minor **minor,
-			 int type)
+
+static struct drm_minor **drm_minor_get_slot(struct drm_device *dev,
+					     unsigned int type)
+{
+	switch (type) {
+	case DRM_MINOR_LEGACY:
+		return &dev->primary;
+	case DRM_MINOR_RENDER:
+		return &dev->render;
+	case DRM_MINOR_CONTROL:
+		return &dev->control;
+	default:
+		return NULL;
+	}
+}
+
+static int drm_minor_alloc(struct drm_device *dev, unsigned int type)
+{
+	struct drm_minor *minor;
+
+	minor = kzalloc(sizeof(*minor), GFP_KERNEL);
+	if (!minor)
+		return -ENOMEM;
+
+	minor->type = type;
+	minor->dev = dev;
+	INIT_LIST_HEAD(&minor->master_list);
+
+	*drm_minor_get_slot(dev, type) = minor;
+	return 0;
+}
+
+static void drm_minor_free(struct drm_device *dev, unsigned int type)
+{
+	struct drm_minor **slot;
+
+	slot = drm_minor_get_slot(dev, type);
+	if (*slot) {
+		kfree(*slot);
+		*slot = NULL;
+	}
+}
+
+static int drm_minor_register(struct drm_device *dev, unsigned int type)
 {
 	struct drm_minor *new_minor;
+	unsigned long flags;
 	int ret;
 	int minor_id;
 
 	DRM_DEBUG("\n");
 
-	minor_id = drm_minor_get_id(dev, type);
+	new_minor = *drm_minor_get_slot(dev, type);
+	if (!new_minor)
+		return 0;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock_irqsave(&drm_minor_lock, flags);
+	minor_id = idr_alloc(&drm_minors_idr,
+			     NULL,
+			     64 * type,
+			     64 * (type + 1),
+			     GFP_NOWAIT);
+	spin_unlock_irqrestore(&drm_minor_lock, flags);
+	idr_preload_end();
+
 	if (minor_id < 0)
 		return minor_id;
 
-	new_minor = kzalloc(sizeof(struct drm_minor), GFP_KERNEL);
-	if (!new_minor) {
-		ret = -ENOMEM;
-		goto err_idr;
-	}
-
-	new_minor->type = type;
-	new_minor->device = MKDEV(DRM_MAJOR, minor_id);
-	new_minor->dev = dev;
 	new_minor->index = minor_id;
-	INIT_LIST_HEAD(&new_minor->master_list);
 
-	idr_replace(&drm_minors_idr, new_minor, minor_id);
-
-#if defined(CONFIG_DEBUG_FS)
 	ret = drm_debugfs_init(new_minor, minor_id, drm_debugfs_root);
 	if (ret) {
 		DRM_ERROR("DRM: Failed to initialize /sys/kernel/debug/dri.\n");
-		goto err_mem;
+		goto err_id;
 	}
-#endif
 
 	ret = drm_sysfs_device_add(new_minor);
 	if (ret) {
-		printk(KERN_ERR
-		       "DRM: Error sysfs_device_add.\n");
+		DRM_ERROR("DRM: Error sysfs_device_add.\n");
 		goto err_debugfs;
 	}
-	*minor = new_minor;
+
+	/* replace NULL with @minor so lookups will succeed from now on */
+	spin_lock_irqsave(&drm_minor_lock, flags);
+	idr_replace(&drm_minors_idr, new_minor, new_minor->index);
+	spin_unlock_irqrestore(&drm_minor_lock, flags);
 
 	DRM_DEBUG("new minor assigned %d\n", minor_id);
 	return 0;
 
-
 err_debugfs:
-#if defined(CONFIG_DEBUG_FS)
 	drm_debugfs_cleanup(new_minor);
-err_mem:
-#endif
-	kfree(new_minor);
-err_idr:
+err_id:
+	spin_lock_irqsave(&drm_minor_lock, flags);
 	idr_remove(&drm_minors_idr, minor_id);
-	*minor = NULL;
+	spin_unlock_irqrestore(&drm_minor_lock, flags);
+	new_minor->index = 0;
 	return ret;
 }
 
-/**
- * drm_unplug_minor - Unplug DRM minor
- * @minor: Minor to unplug
- *
- * Unplugs the given DRM minor but keeps the object. So after this returns,
- * minor->dev is still valid so existing open-files can still access it to get
- * device information from their drm_file ojects.
- * If the minor is already unplugged or if @minor is NULL, nothing is done.
- * The global DRM mutex must be held by the caller.
- */
-static void drm_unplug_minor(struct drm_minor *minor)
+static void drm_minor_unregister(struct drm_device *dev, unsigned int type)
 {
+	struct drm_minor *minor;
+	unsigned long flags;
+
+	minor = *drm_minor_get_slot(dev, type);
 	if (!minor || !minor->kdev)
 		return;
 
-#if defined(CONFIG_DEBUG_FS)
-	drm_debugfs_cleanup(minor);
-#endif
-
-	drm_sysfs_device_remove(minor);
+	spin_lock_irqsave(&drm_minor_lock, flags);
 	idr_remove(&drm_minors_idr, minor->index);
+	spin_unlock_irqrestore(&drm_minor_lock, flags);
+	minor->index = 0;
+
+	drm_debugfs_cleanup(minor);
+	drm_sysfs_device_remove(minor);
 }
 
 /**
- * drm_put_minor - Destroy DRM minor
- * @minor: Minor to destroy
+ * drm_minor_acquire - Acquire a DRM minor
+ * @minor_id: Minor ID of the DRM-minor
  *
- * This calls drm_unplug_minor() on the given minor and then frees it. Nothing
- * is done if @minor is NULL. It is fine to call this on already unplugged
- * minors.
- * The global DRM mutex must be held by the caller.
+ * Looks up the given minor-ID and returns the respective DRM-minor object. The
+ * refence-count of the underlying device is increased so you must release this
+ * object with drm_minor_release().
+ *
+ * As long as you hold this minor, it is guaranteed that the object and the
+ * minor->dev pointer will stay valid! However, the device may get unplugged and
+ * unregistered while you hold the minor.
+ *
+ * Returns:
+ * Pointer to minor-object with increased device-refcount, or PTR_ERR on
+ * failure.
  */
-static void drm_put_minor(struct drm_minor *minor)
+struct drm_minor *drm_minor_acquire(unsigned int minor_id)
 {
-	if (!minor)
-		return;
+	struct drm_minor *minor;
+	unsigned long flags;
 
-	DRM_DEBUG("release secondary minor %d\n", minor->index);
+	spin_lock_irqsave(&drm_minor_lock, flags);
+	minor = idr_find(&drm_minors_idr, minor_id);
+	if (minor)
+		drm_dev_ref(minor->dev);
+	spin_unlock_irqrestore(&drm_minor_lock, flags);
 
-	drm_unplug_minor(minor);
-	kfree(minor);
+	if (!minor) {
+		return ERR_PTR(-ENODEV);
+	} else if (drm_device_is_unplugged(minor->dev)) {
+		drm_dev_unref(minor->dev);
+		return ERR_PTR(-ENODEV);
+	}
+
+	return minor;
+}
+
+/**
+ * drm_minor_release - Release DRM minor
+ * @minor: Pointer to DRM minor object
+ *
+ * Release a minor that was previously acquired via drm_minor_acquire().
+ */
+void drm_minor_release(struct drm_minor *minor)
+{
+	drm_dev_unref(minor->dev);
 }
 
 /**
@@ -392,18 +439,16 @@
 	}
 
 	drm_dev_unregister(dev);
-	drm_dev_free(dev);
+	drm_dev_unref(dev);
 }
 EXPORT_SYMBOL(drm_put_dev);
 
 void drm_unplug_dev(struct drm_device *dev)
 {
 	/* for a USB device */
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
-		drm_unplug_minor(dev->control);
-	if (dev->render)
-		drm_unplug_minor(dev->render);
-	drm_unplug_minor(dev->primary);
+	drm_minor_unregister(dev, DRM_MINOR_LEGACY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 
 	mutex_lock(&drm_global_mutex);
 
@@ -416,6 +461,78 @@
 }
 EXPORT_SYMBOL(drm_unplug_dev);
 
+/*
+ * DRM internal mount
+ * We want to be able to allocate our own "struct address_space" to control
+ * memory-mappings in VRAM (or stolen RAM, ...). However, core MM does not allow
+ * stand-alone address_space objects, so we need an underlying inode. As there
+ * is no way to allocate an independent inode easily, we need a fake internal
+ * VFS mount-point.
+ *
+ * The drm_fs_inode_new() function allocates a new inode, drm_fs_inode_free()
+ * frees it again. You are allowed to use iget() and iput() to get references to
+ * the inode. But each drm_fs_inode_new() call must be paired with exactly one
+ * drm_fs_inode_free() call (which does not have to be the last iput()).
+ * We use drm_fs_inode_*() to manage our internal VFS mount-point and share it
+ * between multiple inode-users. You could, technically, call
+ * iget() + drm_fs_inode_free() directly after alloc and sometime later do an
+ * iput(), but this way you'd end up with a new vfsmount for each inode.
+ */
+
+static int drm_fs_cnt;
+static struct vfsmount *drm_fs_mnt;
+
+static const struct dentry_operations drm_fs_dops = {
+	.d_dname	= simple_dname,
+};
+
+static const struct super_operations drm_fs_sops = {
+	.statfs		= simple_statfs,
+};
+
+static struct dentry *drm_fs_mount(struct file_system_type *fs_type, int flags,
+				   const char *dev_name, void *data)
+{
+	return mount_pseudo(fs_type,
+			    "drm:",
+			    &drm_fs_sops,
+			    &drm_fs_dops,
+			    0x010203ff);
+}
+
+static struct file_system_type drm_fs_type = {
+	.name		= "drm",
+	.owner		= THIS_MODULE,
+	.mount		= drm_fs_mount,
+	.kill_sb	= kill_anon_super,
+};
+
+static struct inode *drm_fs_inode_new(void)
+{
+	struct inode *inode;
+	int r;
+
+	r = simple_pin_fs(&drm_fs_type, &drm_fs_mnt, &drm_fs_cnt);
+	if (r < 0) {
+		DRM_ERROR("Cannot mount pseudo fs: %d\n", r);
+		return ERR_PTR(r);
+	}
+
+	inode = alloc_anon_inode(drm_fs_mnt->mnt_sb);
+	if (IS_ERR(inode))
+		simple_release_fs(&drm_fs_mnt, &drm_fs_cnt);
+
+	return inode;
+}
+
+static void drm_fs_inode_free(struct inode *inode)
+{
+	if (inode) {
+		iput(inode);
+		simple_release_fs(&drm_fs_mnt, &drm_fs_cnt);
+	}
+}
+
 /**
  * drm_dev_alloc - Allocate new drm device
  * @driver: DRM driver to allocate device for
@@ -425,6 +542,9 @@
  * Call drm_dev_register() to advertice the device to user space and register it
  * with other core subsystems.
  *
+ * The initial ref-count of the object is 1. Use drm_dev_ref() and
+ * drm_dev_unref() to take and drop further ref-counts.
+ *
  * RETURNS:
  * Pointer to new DRM device, or NULL if out of memory.
  */
@@ -438,6 +558,7 @@
 	if (!dev)
 		return NULL;
 
+	kref_init(&dev->ref);
 	dev->dev = parent;
 	dev->driver = driver;
 
@@ -452,8 +573,31 @@
 	mutex_init(&dev->struct_mutex);
 	mutex_init(&dev->ctxlist_mutex);
 
-	if (drm_ht_create(&dev->map_hash, 12))
+	dev->anon_inode = drm_fs_inode_new();
+	if (IS_ERR(dev->anon_inode)) {
+		ret = PTR_ERR(dev->anon_inode);
+		DRM_ERROR("Cannot allocate anonymous inode: %d\n", ret);
 		goto err_free;
+	}
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		ret = drm_minor_alloc(dev, DRM_MINOR_CONTROL);
+		if (ret)
+			goto err_minors;
+	}
+
+	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
+		ret = drm_minor_alloc(dev, DRM_MINOR_RENDER);
+		if (ret)
+			goto err_minors;
+	}
+
+	ret = drm_minor_alloc(dev, DRM_MINOR_LEGACY);
+	if (ret)
+		goto err_minors;
+
+	if (drm_ht_create(&dev->map_hash, 12))
+		goto err_minors;
 
 	ret = drm_ctxbitmap_init(dev);
 	if (ret) {
@@ -475,38 +619,68 @@
 	drm_ctxbitmap_cleanup(dev);
 err_ht:
 	drm_ht_remove(&dev->map_hash);
+err_minors:
+	drm_minor_free(dev, DRM_MINOR_LEGACY);
+	drm_minor_free(dev, DRM_MINOR_RENDER);
+	drm_minor_free(dev, DRM_MINOR_CONTROL);
+	drm_fs_inode_free(dev->anon_inode);
 err_free:
 	kfree(dev);
 	return NULL;
 }
 EXPORT_SYMBOL(drm_dev_alloc);
 
-/**
- * drm_dev_free - Free DRM device
- * @dev: DRM device to free
- *
- * Free a DRM device that has previously been allocated via drm_dev_alloc().
- * You must not use kfree() instead or you will leak memory.
- *
- * This must not be called once the device got registered. Use drm_put_dev()
- * instead, which then calls drm_dev_free().
- */
-void drm_dev_free(struct drm_device *dev)
+static void drm_dev_release(struct kref *ref)
 {
-	drm_put_minor(dev->control);
-	drm_put_minor(dev->render);
-	drm_put_minor(dev->primary);
+	struct drm_device *dev = container_of(ref, struct drm_device, ref);
 
 	if (dev->driver->driver_features & DRIVER_GEM)
 		drm_gem_destroy(dev);
 
 	drm_ctxbitmap_cleanup(dev);
 	drm_ht_remove(&dev->map_hash);
+	drm_fs_inode_free(dev->anon_inode);
+
+	drm_minor_free(dev, DRM_MINOR_LEGACY);
+	drm_minor_free(dev, DRM_MINOR_RENDER);
+	drm_minor_free(dev, DRM_MINOR_CONTROL);
 
 	kfree(dev->devname);
 	kfree(dev);
 }
-EXPORT_SYMBOL(drm_dev_free);
+
+/**
+ * drm_dev_ref - Take reference of a DRM device
+ * @dev: device to take reference of or NULL
+ *
+ * This increases the ref-count of @dev by one. You *must* already own a
+ * reference when calling this. Use drm_dev_unref() to drop this reference
+ * again.
+ *
+ * This function never fails. However, this function does not provide *any*
+ * guarantee whether the device is alive or running. It only provides a
+ * reference to the object and the memory associated with it.
+ */
+void drm_dev_ref(struct drm_device *dev)
+{
+	if (dev)
+		kref_get(&dev->ref);
+}
+EXPORT_SYMBOL(drm_dev_ref);
+
+/**
+ * drm_dev_unref - Drop reference of a DRM device
+ * @dev: device to drop reference of or NULL
+ *
+ * This decreases the ref-count of @dev by one. The device is destroyed if the
+ * ref-count drops to zero.
+ */
+void drm_dev_unref(struct drm_device *dev)
+{
+	if (dev)
+		kref_put(&dev->ref, drm_dev_release);
+}
+EXPORT_SYMBOL(drm_dev_unref);
 
 /**
  * drm_dev_register - Register DRM device
@@ -527,26 +701,22 @@
 
 	mutex_lock(&drm_global_mutex);
 
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL);
-		if (ret)
-			goto out_unlock;
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
-		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
-		if (ret)
-			goto err_control_node;
-	}
-
-	ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY);
+	ret = drm_minor_register(dev, DRM_MINOR_CONTROL);
 	if (ret)
-		goto err_render_node;
+		goto err_minors;
+
+	ret = drm_minor_register(dev, DRM_MINOR_RENDER);
+	if (ret)
+		goto err_minors;
+
+	ret = drm_minor_register(dev, DRM_MINOR_LEGACY);
+	if (ret)
+		goto err_minors;
 
 	if (dev->driver->load) {
 		ret = dev->driver->load(dev, flags);
 		if (ret)
-			goto err_primary_node;
+			goto err_minors;
 	}
 
 	/* setup grouping for legacy outputs */
@@ -563,12 +733,10 @@
 err_unload:
 	if (dev->driver->unload)
 		dev->driver->unload(dev);
-err_primary_node:
-	drm_unplug_minor(dev->primary);
-err_render_node:
-	drm_unplug_minor(dev->render);
-err_control_node:
-	drm_unplug_minor(dev->control);
+err_minors:
+	drm_minor_unregister(dev, DRM_MINOR_LEGACY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 out_unlock:
 	mutex_unlock(&drm_global_mutex);
 	return ret;
@@ -581,7 +749,7 @@
  *
  * Unregister the DRM device from the system. This does the reverse of
  * drm_dev_register() but does not deallocate the device. The caller must call
- * drm_dev_free() to free all resources.
+ * drm_dev_unref() to drop their final reference.
  */
 void drm_dev_unregister(struct drm_device *dev)
 {
@@ -600,8 +768,8 @@
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
 		drm_rmmap(dev, r_list->map);
 
-	drm_unplug_minor(dev->control);
-	drm_unplug_minor(dev->render);
-	drm_unplug_minor(dev->primary);
+	drm_minor_unregister(dev, DRM_MINOR_LEGACY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 }
 EXPORT_SYMBOL(drm_dev_unregister);
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index 0f8cb1a..c3406aa 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -30,7 +30,7 @@
 	return 0;
 
 err_free:
-	drm_dev_free(dev);
+	drm_dev_unref(dev);
 	return ret;
 
 }
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index f33902f..b1445b7 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -3,58 +3,69 @@
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
 ccflags-y := -Iinclude/drm
-i915-y := i915_drv.o i915_dma.o i915_irq.o \
-	  i915_gpu_error.o \
+
+# Please keep these build lists sorted!
+
+# core driver code
+i915-y := i915_drv.o \
+	  i915_params.o \
           i915_suspend.o \
-	  i915_gem.o \
+	  i915_sysfs.o \
+	  intel_pm.o
+i915-$(CONFIG_COMPAT)   += i915_ioc32.o
+i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
+
+# GEM code
+i915-y += i915_cmd_parser.o \
 	  i915_gem_context.o \
 	  i915_gem_debug.o \
+	  i915_gem_dmabuf.o \
 	  i915_gem_evict.o \
 	  i915_gem_execbuffer.o \
 	  i915_gem_gtt.o \
+	  i915_gem.o \
 	  i915_gem_stolen.o \
 	  i915_gem_tiling.o \
-	  i915_params.o \
-	  i915_sysfs.o \
+	  i915_gpu_error.o \
+	  i915_irq.o \
 	  i915_trace_points.o \
-	  i915_ums.o \
+	  intel_ringbuffer.o \
+	  intel_uncore.o
+
+# modesetting core code
+i915-y += intel_bios.o \
 	  intel_display.o \
+	  intel_modes.o \
+	  intel_overlay.o \
+	  intel_sideband.o \
+	  intel_sprite.o
+i915-$(CONFIG_ACPI)		+= intel_acpi.o intel_opregion.o
+i915-$(CONFIG_DRM_I915_FBDEV)	+= intel_fbdev.o
+
+# modesetting output/encoder code
+i915-y += dvo_ch7017.o \
+	  dvo_ch7xxx.o \
+	  dvo_ivch.o \
+	  dvo_ns2501.o \
+	  dvo_sil164.o \
+	  dvo_tfp410.o \
 	  intel_crt.o \
-	  intel_lvds.o \
-	  intel_dsi.o \
-	  intel_dsi_cmd.o \
-	  intel_dsi_pll.o \
-	  intel_bios.o \
 	  intel_ddi.o \
 	  intel_dp.o \
-	  intel_hdmi.o \
-	  intel_sdvo.o \
-	  intel_modes.o \
-	  intel_panel.o \
-	  intel_pm.o \
-	  intel_i2c.o \
-	  intel_tv.o \
+	  intel_dsi_cmd.o \
+	  intel_dsi.o \
+	  intel_dsi_pll.o \
 	  intel_dvo.o \
-	  intel_ringbuffer.o \
-	  intel_overlay.o \
-	  intel_sprite.o \
-	  intel_sideband.o \
-	  intel_uncore.o \
-	  dvo_ch7xxx.o \
-	  dvo_ch7017.o \
-	  dvo_ivch.o \
-	  dvo_tfp410.o \
-	  dvo_sil164.o \
-	  dvo_ns2501.o \
-	  i915_gem_dmabuf.o
+	  intel_hdmi.o \
+	  intel_i2c.o \
+	  intel_lvds.o \
+	  intel_panel.o \
+	  intel_sdvo.o \
+	  intel_tv.o
 
-i915-$(CONFIG_COMPAT)   += i915_ioc32.o
-
-i915-$(CONFIG_ACPI)	+= intel_acpi.o intel_opregion.o
-
-i915-$(CONFIG_DRM_I915_FBDEV) += intel_fbdev.o
-
-i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
+# legacy horrors
+i915-y += i915_dma.o \
+	  i915_ums.o
 
 obj-$(CONFIG_DRM_I915)  += i915.o
 
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
new file mode 100644
index 0000000..7a5756e
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -0,0 +1,485 @@
+/*
+ * Copyright © 2013 Intel Corporation
+ *
+ * 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:
+ *    Brad Volkin <bradley.d.volkin@intel.com>
+ *
+ */
+
+#include "i915_drv.h"
+
+/**
+ * DOC: i915 batch buffer command parser
+ *
+ * Motivation:
+ * Certain OpenGL features (e.g. transform feedback, performance monitoring)
+ * require userspace code to submit batches containing commands such as
+ * MI_LOAD_REGISTER_IMM to access various registers. Unfortunately, some
+ * generations of the hardware will noop these commands in "unsecure" batches
+ * (which includes all userspace batches submitted via i915) even though the
+ * commands may be safe and represent the intended programming model of the
+ * device.
+ *
+ * The software command parser is similar in operation to the command parsing
+ * done in hardware for unsecure batches. However, the software parser allows
+ * some operations that would be noop'd by hardware, if the parser determines
+ * the operation is safe, and submits the batch as "secure" to prevent hardware
+ * parsing.
+ *
+ * Threats:
+ * At a high level, the hardware (and software) checks attempt to prevent
+ * granting userspace undue privileges. There are three categories of privilege.
+ *
+ * First, commands which are explicitly defined as privileged or which should
+ * only be used by the kernel driver. The parser generally rejects such
+ * commands, though it may allow some from the drm master process.
+ *
+ * Second, commands which access registers. To support correct/enhanced
+ * userspace functionality, particularly certain OpenGL extensions, the parser
+ * provides a whitelist of registers which userspace may safely access (for both
+ * normal and drm master processes).
+ *
+ * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
+ * The parser always rejects such commands.
+ *
+ * The majority of the problematic commands fall in the MI_* range, with only a
+ * few specific commands on each ring (e.g. PIPE_CONTROL and MI_FLUSH_DW).
+ *
+ * Implementation:
+ * Each ring maintains tables of commands and registers which the parser uses in
+ * scanning batch buffers submitted to that ring.
+ *
+ * Since the set of commands that the parser must check for is significantly
+ * smaller than the number of commands supported, the parser tables contain only
+ * those commands required by the parser. This generally works because command
+ * opcode ranges have standard command length encodings. So for commands that
+ * the parser does not need to check, it can easily skip them. This is
+ * implementated via a per-ring length decoding vfunc.
+ *
+ * Unfortunately, there are a number of commands that do not follow the standard
+ * length encoding for their opcode range, primarily amongst the MI_* commands.
+ * To handle this, the parser provides a way to define explicit "skip" entries
+ * in the per-ring command tables.
+ *
+ * Other command table entries map fairly directly to high level categories
+ * mentioned above: rejected, master-only, register whitelist. The parser
+ * implements a number of checks, including the privileged memory checks, via a
+ * general bitmasking mechanism.
+ */
+
+static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT;
+	u32 subclient =
+		(cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT)
+		return 0x3F;
+	else if (client == INSTR_RC_CLIENT) {
+		if (subclient == INSTR_MEDIA_SUBCLIENT)
+			return 0xFFFF;
+		else
+			return 0xFF;
+	}
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal rcs cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
+static u32 gen7_bsd_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT;
+	u32 subclient =
+		(cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT)
+		return 0x3F;
+	else if (client == INSTR_RC_CLIENT) {
+		if (subclient == INSTR_MEDIA_SUBCLIENT)
+			return 0xFFF;
+		else
+			return 0xFF;
+	}
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal bsd cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
+static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT)
+		return 0x3F;
+	else if (client == INSTR_BC_CLIENT)
+		return 0xFF;
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
+static void validate_cmds_sorted(struct intel_ring_buffer *ring)
+{
+	int i;
+
+	if (!ring->cmd_tables || ring->cmd_table_count == 0)
+		return;
+
+	for (i = 0; i < ring->cmd_table_count; i++) {
+		const struct drm_i915_cmd_table *table = &ring->cmd_tables[i];
+		u32 previous = 0;
+		int j;
+
+		for (j = 0; j < table->count; j++) {
+			const struct drm_i915_cmd_descriptor *desc =
+				&table->table[i];
+			u32 curr = desc->cmd.value & desc->cmd.mask;
+
+			if (curr < previous)
+				DRM_ERROR("CMD: table not sorted ring=%d table=%d entry=%d cmd=0x%08X prev=0x%08X\n",
+					  ring->id, i, j, curr, previous);
+
+			previous = curr;
+		}
+	}
+}
+
+static void check_sorted(int ring_id, const u32 *reg_table, int reg_count)
+{
+	int i;
+	u32 previous = 0;
+
+	for (i = 0; i < reg_count; i++) {
+		u32 curr = reg_table[i];
+
+		if (curr < previous)
+			DRM_ERROR("CMD: table not sorted ring=%d entry=%d reg=0x%08X prev=0x%08X\n",
+				  ring_id, i, curr, previous);
+
+		previous = curr;
+	}
+}
+
+static void validate_regs_sorted(struct intel_ring_buffer *ring)
+{
+	check_sorted(ring->id, ring->reg_table, ring->reg_count);
+	check_sorted(ring->id, ring->master_reg_table, ring->master_reg_count);
+}
+
+/**
+ * i915_cmd_parser_init_ring() - set cmd parser related fields for a ringbuffer
+ * @ring: the ringbuffer to initialize
+ *
+ * Optionally initializes fields related to batch buffer command parsing in the
+ * struct intel_ring_buffer based on whether the platform requires software
+ * command parsing.
+ */
+void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring)
+{
+	if (!IS_GEN7(ring->dev))
+		return;
+
+	switch (ring->id) {
+	case RCS:
+		ring->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
+		break;
+	case VCS:
+		ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
+		break;
+	case BCS:
+		ring->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
+		break;
+	case VECS:
+		/* VECS can use the same length_mask function as VCS */
+		ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
+		break;
+	default:
+		DRM_ERROR("CMD: cmd_parser_init with unknown ring: %d\n",
+			  ring->id);
+		BUG();
+	}
+
+	validate_cmds_sorted(ring);
+	validate_regs_sorted(ring);
+}
+
+static const struct drm_i915_cmd_descriptor*
+find_cmd_in_table(const struct drm_i915_cmd_table *table,
+		  u32 cmd_header)
+{
+	int i;
+
+	for (i = 0; i < table->count; i++) {
+		const struct drm_i915_cmd_descriptor *desc = &table->table[i];
+		u32 masked_cmd = desc->cmd.mask & cmd_header;
+		u32 masked_value = desc->cmd.value & desc->cmd.mask;
+
+		if (masked_cmd == masked_value)
+			return desc;
+	}
+
+	return NULL;
+}
+
+/*
+ * Returns a pointer to a descriptor for the command specified by cmd_header.
+ *
+ * The caller must supply space for a default descriptor via the default_desc
+ * parameter. If no descriptor for the specified command exists in the ring's
+ * command parser tables, this function fills in default_desc based on the
+ * ring's default length encoding and returns default_desc.
+ */
+static const struct drm_i915_cmd_descriptor*
+find_cmd(struct intel_ring_buffer *ring,
+	 u32 cmd_header,
+	 struct drm_i915_cmd_descriptor *default_desc)
+{
+	u32 mask;
+	int i;
+
+	for (i = 0; i < ring->cmd_table_count; i++) {
+		const struct drm_i915_cmd_descriptor *desc;
+
+		desc = find_cmd_in_table(&ring->cmd_tables[i], cmd_header);
+		if (desc)
+			return desc;
+	}
+
+	mask = ring->get_cmd_length_mask(cmd_header);
+	if (!mask)
+		return NULL;
+
+	BUG_ON(!default_desc);
+	default_desc->flags = CMD_DESC_SKIP;
+	default_desc->length.mask = mask;
+
+	return default_desc;
+}
+
+static bool valid_reg(const u32 *table, int count, u32 addr)
+{
+	if (table && count != 0) {
+		int i;
+
+		for (i = 0; i < count; i++) {
+			if (table[i] == addr)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static u32 *vmap_batch(struct drm_i915_gem_object *obj)
+{
+	int i;
+	void *addr = NULL;
+	struct sg_page_iter sg_iter;
+	struct page **pages;
+
+	pages = drm_malloc_ab(obj->base.size >> PAGE_SHIFT, sizeof(*pages));
+	if (pages == NULL) {
+		DRM_DEBUG_DRIVER("Failed to get space for pages\n");
+		goto finish;
+	}
+
+	i = 0;
+	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
+		pages[i] = sg_page_iter_page(&sg_iter);
+		i++;
+	}
+
+	addr = vmap(pages, i, 0, PAGE_KERNEL);
+	if (addr == NULL) {
+		DRM_DEBUG_DRIVER("Failed to vmap pages\n");
+		goto finish;
+	}
+
+finish:
+	if (pages)
+		drm_free_large(pages);
+	return (u32*)addr;
+}
+
+/**
+ * i915_needs_cmd_parser() - should a given ring use software command parsing?
+ * @ring: the ring in question
+ *
+ * Only certain platforms require software batch buffer command parsing, and
+ * only when enabled via module paramter.
+ *
+ * Return: true if the ring requires software command parsing
+ */
+bool i915_needs_cmd_parser(struct intel_ring_buffer *ring)
+{
+	/* No command tables indicates a platform without parsing */
+	if (!ring->cmd_tables)
+		return false;
+
+	return (i915.enable_cmd_parser == 1);
+}
+
+#define LENGTH_BIAS 2
+
+/**
+ * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
+ * @ring: the ring on which the batch is to execute
+ * @batch_obj: the batch buffer in question
+ * @batch_start_offset: byte offset in the batch at which execution starts
+ * @is_master: is the submitting process the drm master?
+ *
+ * Parses the specified batch buffer looking for privilege violations as
+ * described in the overview.
+ *
+ * Return: non-zero if the parser finds violations or otherwise fails
+ */
+int i915_parse_cmds(struct intel_ring_buffer *ring,
+		    struct drm_i915_gem_object *batch_obj,
+		    u32 batch_start_offset,
+		    bool is_master)
+{
+	int ret = 0;
+	u32 *cmd, *batch_base, *batch_end;
+	struct drm_i915_cmd_descriptor default_desc = { 0 };
+	int needs_clflush = 0;
+
+	ret = i915_gem_obj_prepare_shmem_read(batch_obj, &needs_clflush);
+	if (ret) {
+		DRM_DEBUG_DRIVER("CMD: failed to prep read\n");
+		return ret;
+	}
+
+	batch_base = vmap_batch(batch_obj);
+	if (!batch_base) {
+		DRM_DEBUG_DRIVER("CMD: Failed to vmap batch\n");
+		i915_gem_object_unpin_pages(batch_obj);
+		return -ENOMEM;
+	}
+
+	if (needs_clflush)
+		drm_clflush_virt_range((char *)batch_base, batch_obj->base.size);
+
+	cmd = batch_base + (batch_start_offset / sizeof(*cmd));
+	batch_end = cmd + (batch_obj->base.size / sizeof(*batch_end));
+
+	while (cmd < batch_end) {
+		const struct drm_i915_cmd_descriptor *desc;
+		u32 length;
+
+		if (*cmd == MI_BATCH_BUFFER_END)
+			break;
+
+		desc = find_cmd(ring, *cmd, &default_desc);
+		if (!desc) {
+			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
+					 *cmd);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (desc->flags & CMD_DESC_FIXED)
+			length = desc->length.fixed;
+		else
+			length = ((*cmd & desc->length.mask) + LENGTH_BIAS);
+
+		if ((batch_end - cmd) < length) {
+			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%d batchlen=%ld\n",
+					 *cmd,
+					 length,
+					 batch_end - cmd);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (desc->flags & CMD_DESC_REJECT) {
+			DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd);
+			ret = -EINVAL;
+			break;
+		}
+
+		if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
+			DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
+					 *cmd);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (desc->flags & CMD_DESC_REGISTER) {
+			u32 reg_addr = cmd[desc->reg.offset] & desc->reg.mask;
+
+			if (!valid_reg(ring->reg_table,
+				       ring->reg_count, reg_addr)) {
+				if (!is_master ||
+				    !valid_reg(ring->master_reg_table,
+					       ring->master_reg_count,
+					       reg_addr)) {
+					DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (ring=%d)\n",
+							 reg_addr,
+							 *cmd,
+							 ring->id);
+					ret = -EINVAL;
+					break;
+				}
+			}
+		}
+
+		if (desc->flags & CMD_DESC_BITMASK) {
+			int i;
+
+			for (i = 0; i < MAX_CMD_DESC_BITMASKS; i++) {
+				u32 dword;
+
+				if (desc->bits[i].mask == 0)
+					break;
+
+				dword = cmd[desc->bits[i].offset] &
+					desc->bits[i].mask;
+
+				if (dword != desc->bits[i].expected) {
+					DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (ring=%d)\n",
+							 *cmd,
+							 desc->bits[i].mask,
+							 desc->bits[i].expected,
+							 dword, ring->id);
+					ret = -EINVAL;
+					break;
+				}
+			}
+
+			if (ret)
+				break;
+		}
+
+		cmd += length;
+	}
+
+	if (cmd >= batch_end) {
+		DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
+		ret = -EINVAL;
+	}
+
+	vunmap(batch_base);
+
+	i915_gem_object_unpin_pages(batch_obj);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2dc05c3..a90d31c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -602,7 +602,6 @@
 	intel_runtime_pm_get(dev_priv);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
-		int i;
 		seq_printf(m, "Master Interrupt Control:\t%08x\n",
 			   I915_READ(GEN8_MASTER_IRQ));
 
@@ -615,16 +614,16 @@
 				   i, I915_READ(GEN8_GT_IER(i)));
 		}
 
-		for_each_pipe(i) {
+		for_each_pipe(pipe) {
 			seq_printf(m, "Pipe %c IMR:\t%08x\n",
-				   pipe_name(i),
-				   I915_READ(GEN8_DE_PIPE_IMR(i)));
+				   pipe_name(pipe),
+				   I915_READ(GEN8_DE_PIPE_IMR(pipe)));
 			seq_printf(m, "Pipe %c IIR:\t%08x\n",
-				   pipe_name(i),
-				   I915_READ(GEN8_DE_PIPE_IIR(i)));
+				   pipe_name(pipe),
+				   I915_READ(GEN8_DE_PIPE_IIR(pipe)));
 			seq_printf(m, "Pipe %c IER:\t%08x\n",
-				   pipe_name(i),
-				   I915_READ(GEN8_DE_PIPE_IER(i)));
+				   pipe_name(pipe),
+				   I915_READ(GEN8_DE_PIPE_IER(pipe)));
 		}
 
 		seq_printf(m, "Display Engine port interrupt mask:\t%08x\n",
@@ -1348,6 +1347,8 @@
 		return 0;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	if (intel_fbc_enabled(dev)) {
 		seq_puts(m, "FBC enabled\n");
 	} else {
@@ -1391,6 +1392,9 @@
 		}
 		seq_putc(m, '\n');
 	}
+
+	intel_runtime_pm_put(dev_priv);
+
 	return 0;
 }
 
@@ -1405,11 +1409,15 @@
 		return 0;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	if (IS_BROADWELL(dev) || I915_READ(IPS_CTL) & IPS_ENABLE)
 		seq_puts(m, "enabled\n");
 	else
 		seq_puts(m, "disabled\n");
 
+	intel_runtime_pm_put(dev_priv);
+
 	return 0;
 }
 
@@ -1420,6 +1428,8 @@
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	bool sr_enabled = false;
 
+	intel_runtime_pm_get(dev_priv);
+
 	if (HAS_PCH_SPLIT(dev))
 		sr_enabled = I915_READ(WM1_LP_ILK) & WM1_LP_SR_EN;
 	else if (IS_CRESTLINE(dev) || IS_I945G(dev) || IS_I945GM(dev))
@@ -1429,6 +1439,8 @@
 	else if (IS_PINEVIEW(dev))
 		sr_enabled = I915_READ(DSPFW3) & PINEVIEW_SELF_REFRESH_EN;
 
+	intel_runtime_pm_put(dev_priv);
+
 	seq_printf(m, "self-refresh: %s\n",
 		   sr_enabled ? "enabled" : "disabled");
 
@@ -1468,7 +1480,7 @@
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret = 0;
 	int gpu_freq, ia_freq;
 
 	if (!(IS_GEN6(dev) || IS_GEN7(dev))) {
@@ -1476,12 +1488,13 @@
 		return 0;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
 
 	ret = mutex_lock_interruptible(&dev_priv->rps.hw_lock);
 	if (ret)
-		return ret;
-	intel_runtime_pm_get(dev_priv);
+		goto out;
 
 	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
 
@@ -1498,10 +1511,11 @@
 			   ((ia_freq >> 8) & 0xff) * 100);
 	}
 
-	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
-	return 0;
+out:
+	intel_runtime_pm_put(dev_priv);
+	return ret;
 }
 
 static int i915_gfxec(struct seq_file *m, void *unused)
@@ -1757,7 +1771,7 @@
 		return;
 
 	seq_printf(m, "Page directories: %d\n", ppgtt->num_pd_pages);
-	seq_printf(m, "Page tables: %d\n", ppgtt->num_pt_pages);
+	seq_printf(m, "Page tables: %d\n", ppgtt->num_pd_entries);
 	for_each_ring(ring, dev_priv, unused) {
 		seq_printf(m, "%s\n", ring->name);
 		for (i = 0; i < 4; i++) {
@@ -1937,6 +1951,9 @@
 		if (connector->base.dpms != DRM_MODE_DPMS_ON)
 			continue;
 
+		if (!connector->base.encoder)
+			continue;
+
 		encoder = to_intel_encoder(connector->base.encoder);
 		if (encoder->type != INTEL_OUTPUT_EDP)
 			continue;
@@ -1969,12 +1986,16 @@
 	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
+	intel_runtime_pm_get(dev_priv);
+
 	rdmsrl(MSR_RAPL_POWER_UNIT, power);
 	power = (power & 0x1f00) >> 8;
 	units = 1000000 / (1 << power); /* convert to uJ */
 	power = I915_READ(MCH_SECP_NRG_STTS);
 	power *= units;
 
+	intel_runtime_pm_put(dev_priv);
+
 	seq_printf(m, "%llu", (long long unsigned)power);
 
 	return 0;
@@ -1994,7 +2015,7 @@
 	mutex_lock(&dev_priv->pc8.lock);
 	seq_printf(m, "Requirements met: %s\n",
 		   yesno(dev_priv->pc8.requirements_met));
-	seq_printf(m, "GPU idle: %s\n", yesno(dev_priv->pc8.gpu_idle));
+	seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->mm.busy));
 	seq_printf(m, "Disable count: %d\n", dev_priv->pc8.disable_count);
 	seq_printf(m, "IRQs disabled: %s\n",
 		   yesno(dev_priv->pc8.irqs_disabled));
@@ -2027,6 +2048,28 @@
 		return "TRANSCODER_C";
 	case POWER_DOMAIN_TRANSCODER_EDP:
 		return "TRANSCODER_EDP";
+	case POWER_DOMAIN_PORT_DDI_A_2_LANES:
+		return "PORT_DDI_A_2_LANES";
+	case POWER_DOMAIN_PORT_DDI_A_4_LANES:
+		return "PORT_DDI_A_4_LANES";
+	case POWER_DOMAIN_PORT_DDI_B_2_LANES:
+		return "PORT_DDI_B_2_LANES";
+	case POWER_DOMAIN_PORT_DDI_B_4_LANES:
+		return "PORT_DDI_B_4_LANES";
+	case POWER_DOMAIN_PORT_DDI_C_2_LANES:
+		return "PORT_DDI_C_2_LANES";
+	case POWER_DOMAIN_PORT_DDI_C_4_LANES:
+		return "PORT_DDI_C_4_LANES";
+	case POWER_DOMAIN_PORT_DDI_D_2_LANES:
+		return "PORT_DDI_D_2_LANES";
+	case POWER_DOMAIN_PORT_DDI_D_4_LANES:
+		return "PORT_DDI_D_4_LANES";
+	case POWER_DOMAIN_PORT_DSI:
+		return "PORT_DSI";
+	case POWER_DOMAIN_PORT_CRT:
+		return "PORT_CRT";
+	case POWER_DOMAIN_PORT_OTHER:
+		return "PORT_OTHER";
 	case POWER_DOMAIN_VGA:
 		return "VGA";
 	case POWER_DOMAIN_AUDIO:
@@ -2074,6 +2117,168 @@
 	return 0;
 }
 
+static void intel_seq_print_mode(struct seq_file *m, int tabs,
+				 struct drm_display_mode *mode)
+{
+	int i;
+
+	for (i = 0; i < tabs; i++)
+		seq_putc(m, '\t');
+
+	seq_printf(m, "id %d:\"%s\" freq %d clock %d hdisp %d hss %d hse %d htot %d vdisp %d vss %d vse %d vtot %d type 0x%x flags 0x%x\n",
+		   mode->base.id, mode->name,
+		   mode->vrefresh, mode->clock,
+		   mode->hdisplay, mode->hsync_start,
+		   mode->hsync_end, mode->htotal,
+		   mode->vdisplay, mode->vsync_start,
+		   mode->vsync_end, mode->vtotal,
+		   mode->type, mode->flags);
+}
+
+static void intel_encoder_info(struct seq_file *m,
+			       struct intel_crtc *intel_crtc,
+			       struct intel_encoder *intel_encoder)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct intel_connector *intel_connector;
+	struct drm_encoder *encoder;
+
+	encoder = &intel_encoder->base;
+	seq_printf(m, "\tencoder %d: type: %s, connectors:\n",
+		   encoder->base.id, drm_get_encoder_name(encoder));
+	for_each_connector_on_encoder(dev, encoder, intel_connector) {
+		struct drm_connector *connector = &intel_connector->base;
+		seq_printf(m, "\t\tconnector %d: type: %s, status: %s",
+			   connector->base.id,
+			   drm_get_connector_name(connector),
+			   drm_get_connector_status_name(connector->status));
+		if (connector->status == connector_status_connected) {
+			struct drm_display_mode *mode = &crtc->mode;
+			seq_printf(m, ", mode:\n");
+			intel_seq_print_mode(m, 2, mode);
+		} else {
+			seq_putc(m, '\n');
+		}
+	}
+}
+
+static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct intel_encoder *intel_encoder;
+
+	seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
+		   crtc->fb->base.id, crtc->x, crtc->y,
+		   crtc->fb->width, crtc->fb->height);
+	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
+		intel_encoder_info(m, intel_crtc, intel_encoder);
+}
+
+static void intel_panel_info(struct seq_file *m, struct intel_panel *panel)
+{
+	struct drm_display_mode *mode = panel->fixed_mode;
+
+	seq_printf(m, "\tfixed mode:\n");
+	intel_seq_print_mode(m, 2, mode);
+}
+
+static void intel_dp_info(struct seq_file *m,
+			  struct intel_connector *intel_connector)
+{
+	struct intel_encoder *intel_encoder = intel_connector->encoder;
+	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
+
+	seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]);
+	seq_printf(m, "\taudio support: %s\n", intel_dp->has_audio ? "yes" :
+		   "no");
+	if (intel_encoder->type == INTEL_OUTPUT_EDP)
+		intel_panel_info(m, &intel_connector->panel);
+}
+
+static void intel_hdmi_info(struct seq_file *m,
+			    struct intel_connector *intel_connector)
+{
+	struct intel_encoder *intel_encoder = intel_connector->encoder;
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
+
+	seq_printf(m, "\taudio support: %s\n", intel_hdmi->has_audio ? "yes" :
+		   "no");
+}
+
+static void intel_lvds_info(struct seq_file *m,
+			    struct intel_connector *intel_connector)
+{
+	intel_panel_info(m, &intel_connector->panel);
+}
+
+static void intel_connector_info(struct seq_file *m,
+				 struct drm_connector *connector)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_encoder *intel_encoder = intel_connector->encoder;
+	struct drm_display_mode *mode;
+
+	seq_printf(m, "connector %d: type %s, status: %s\n",
+		   connector->base.id, drm_get_connector_name(connector),
+		   drm_get_connector_status_name(connector->status));
+	if (connector->status == connector_status_connected) {
+		seq_printf(m, "\tname: %s\n", connector->display_info.name);
+		seq_printf(m, "\tphysical dimensions: %dx%dmm\n",
+			   connector->display_info.width_mm,
+			   connector->display_info.height_mm);
+		seq_printf(m, "\tsubpixel order: %s\n",
+			   drm_get_subpixel_order_name(connector->display_info.subpixel_order));
+		seq_printf(m, "\tCEA rev: %d\n",
+			   connector->display_info.cea_rev);
+	}
+	if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+	    intel_encoder->type == INTEL_OUTPUT_EDP)
+		intel_dp_info(m, intel_connector);
+	else if (intel_encoder->type == INTEL_OUTPUT_HDMI)
+		intel_hdmi_info(m, intel_connector);
+	else if (intel_encoder->type == INTEL_OUTPUT_LVDS)
+		intel_lvds_info(m, intel_connector);
+
+	seq_printf(m, "\tmodes:\n");
+	list_for_each_entry(mode, &connector->modes, head)
+		intel_seq_print_mode(m, 2, mode);
+}
+
+static int i915_display_info(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_crtc *crtc;
+	struct drm_connector *connector;
+
+	drm_modeset_lock_all(dev);
+	seq_printf(m, "CRTC info\n");
+	seq_printf(m, "---------\n");
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+
+		seq_printf(m, "CRTC %d: pipe: %c, active: %s\n",
+			   crtc->base.id, pipe_name(intel_crtc->pipe),
+			   intel_crtc->active ? "yes" : "no");
+		if (intel_crtc->active)
+			intel_crtc_info(m, intel_crtc);
+	}
+
+	seq_printf(m, "\n");
+	seq_printf(m, "Connector info\n");
+	seq_printf(m, "--------------\n");
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+		intel_connector_info(m, connector);
+	}
+	drm_modeset_unlock_all(dev);
+
+	return 0;
+}
+
 struct pipe_crc_info {
 	const char *name;
 	struct drm_device *dev;
@@ -3006,9 +3211,8 @@
 {
 	struct drm_device *dev = data;
 
-	DRM_INFO("Manually setting wedged to %llu\n", val);
-	i915_handle_error(dev, val);
-
+	i915_handle_error(dev, val,
+			  "Manually setting wedged to %llu", val);
 	return 0;
 }
 
@@ -3519,6 +3723,7 @@
 	{"i915_energy_uJ", i915_energy_uJ, 0},
 	{"i915_pc8_status", i915_pc8_status, 0},
 	{"i915_power_domain_info", i915_power_domain_info, 0},
+	{"i915_display_info", i915_display_info, 0},
 };
 #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 258b1be..e4d2b9f 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -626,9 +626,8 @@
 			    struct drm_file *file_priv)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
-	drm_i915_sarea_t *sarea_priv = (drm_i915_sarea_t *)
-	    master_priv->sarea_priv;
+	struct drm_i915_master_private *master_priv;
+	drm_i915_sarea_t *sarea_priv;
 	drm_i915_batchbuffer_t *batch = data;
 	int ret;
 	struct drm_clip_rect *cliprects = NULL;
@@ -636,6 +635,9 @@
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
+	master_priv = dev->primary->master->driver_priv;
+	sarea_priv = (drm_i915_sarea_t *) master_priv->sarea_priv;
+
 	if (!dev_priv->dri1.allow_batchbuffer) {
 		DRM_ERROR("Batchbuffer ioctl disabled\n");
 		return -EINVAL;
@@ -682,9 +684,8 @@
 			  struct drm_file *file_priv)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
-	drm_i915_sarea_t *sarea_priv = (drm_i915_sarea_t *)
-	    master_priv->sarea_priv;
+	struct drm_i915_master_private *master_priv;
+	drm_i915_sarea_t *sarea_priv;
 	drm_i915_cmdbuffer_t *cmdbuf = data;
 	struct drm_clip_rect *cliprects = NULL;
 	void *batch_data;
@@ -696,6 +697,9 @@
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
+	master_priv = dev->primary->master->driver_priv;
+	sarea_priv = (drm_i915_sarea_t *) master_priv->sarea_priv;
+
 	RING_LOCK_TEST_WITH_RETURN(dev, file_priv);
 
 	if (cmdbuf->num_cliprects < 0)
@@ -1317,12 +1321,12 @@
 	if (ret)
 		goto cleanup_vga_switcheroo;
 
+	intel_power_domains_init_hw(dev_priv);
+
 	ret = drm_irq_install(dev);
 	if (ret)
 		goto cleanup_gem_stolen;
 
-	intel_power_domains_init_hw(dev);
-
 	/* Important: The output setup functions called by modeset_init need
 	 * working irqs for e.g. gmbus and dp aux transfers. */
 	intel_modeset_init(dev);
@@ -1339,7 +1343,7 @@
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
 	dev->vblank_disable_allowed = true;
 	if (INTEL_INFO(dev)->num_pipes == 0) {
-		intel_display_power_put(dev, POWER_DOMAIN_VGA);
+		intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
 		return 0;
 	}
 
@@ -1377,7 +1381,7 @@
 	WARN_ON(dev_priv->mm.aliasing_ppgtt);
 	drm_mm_takedown(&dev_priv->gtt.base.mm);
 cleanup_power:
-	intel_display_power_put(dev, POWER_DOMAIN_VGA);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
 	i915_gem_cleanup_stolen(dev);
@@ -1442,7 +1446,7 @@
 
 static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 {
-	const struct intel_device_info *info = dev_priv->info;
+	const struct intel_device_info *info = &dev_priv->info;
 
 #define PRINT_S(name) "%s"
 #define SEP_EMPTY
@@ -1459,6 +1463,62 @@
 #undef SEP_COMMA
 }
 
+/*
+ * Determine various intel_device_info fields at runtime.
+ *
+ * Use it when either:
+ *   - it's judged too laborious to fill n static structures with the limit
+ *     when a simple if statement does the job,
+ *   - run-time checks (eg read fuse/strap registers) are needed.
+ *
+ * This function needs to be called:
+ *   - after the MMIO has been setup as we are reading registers,
+ *   - after the PCH has been detected,
+ *   - before the first usage of the fields it can tweak.
+ */
+static void intel_device_info_runtime_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_device_info *info;
+	enum pipe pipe;
+
+	info = (struct intel_device_info *)&dev_priv->info;
+
+	if (IS_VALLEYVIEW(dev))
+		for_each_pipe(pipe)
+			info->num_sprites[pipe] = 2;
+	else
+		for_each_pipe(pipe)
+			info->num_sprites[pipe] = 1;
+
+	if (i915.disable_display) {
+		DRM_INFO("Display disabled (module parameter)\n");
+		info->num_pipes = 0;
+	} else if (info->num_pipes > 0 &&
+		   (INTEL_INFO(dev)->gen == 7 || INTEL_INFO(dev)->gen == 8) &&
+		   !IS_VALLEYVIEW(dev)) {
+		u32 fuse_strap = I915_READ(FUSE_STRAP);
+		u32 sfuse_strap = I915_READ(SFUSE_STRAP);
+
+		/*
+		 * SFUSE_STRAP is supposed to have a bit signalling the display
+		 * is fused off. Unfortunately it seems that, at least in
+		 * certain cases, fused off display means that PCH display
+		 * reads don't land anywhere. In that case, we read 0s.
+		 *
+		 * On CPT/PPT, we can detect this case as SFUSE_STRAP_FUSE_LOCK
+		 * should be set when taking over after the firmware.
+		 */
+		if (fuse_strap & ILK_INTERNAL_DISPLAY_DISABLE ||
+		    sfuse_strap & SFUSE_STRAP_DISPLAY_DISABLED ||
+		    (dev_priv->pch_type == PCH_CPT &&
+		     !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) {
+			DRM_INFO("Display fused off, disabling\n");
+			info->num_pipes = 0;
+		}
+	}
+}
+
 /**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
@@ -1473,7 +1533,7 @@
 int i915_driver_load(struct drm_device *dev, unsigned long flags)
 {
 	struct drm_i915_private *dev_priv;
-	struct intel_device_info *info;
+	struct intel_device_info *info, *device_info;
 	int ret = 0, mmio_bar, mmio_size;
 	uint32_t aperture_size;
 
@@ -1496,7 +1556,10 @@
 
 	dev->dev_private = (void *)dev_priv;
 	dev_priv->dev = dev;
-	dev_priv->info = info;
+
+	/* copy initial configuration to dev_priv->info */
+	device_info = (struct intel_device_info *)&dev_priv->info;
+	*device_info = *info;
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
@@ -1635,9 +1698,7 @@
 	if (!IS_I945G(dev) && !IS_I945GM(dev))
 		pci_enable_msi(dev->pdev);
 
-	dev_priv->num_plane = 1;
-	if (IS_VALLEYVIEW(dev))
-		dev_priv->num_plane = 2;
+	intel_device_info_runtime_init(dev);
 
 	if (INTEL_INFO(dev)->num_pipes) {
 		ret = drm_vblank_init(dev, INTEL_INFO(dev)->num_pipes);
@@ -1645,7 +1706,7 @@
 			goto out_gem_unload;
 	}
 
-	intel_power_domains_init(dev);
+	intel_power_domains_init(dev_priv);
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		ret = i915_load_modeset_init(dev);
@@ -1674,7 +1735,7 @@
 	return 0;
 
 out_power_well:
-	intel_power_domains_remove(dev);
+	intel_power_domains_remove(dev_priv);
 	drm_vblank_cleanup(dev);
 out_gem_unload:
 	if (dev_priv->mm.inactive_shrinker.scan_objects)
@@ -1724,8 +1785,8 @@
 	/* The i915.ko module is still not prepared to be loaded when
 	 * the power well is not enabled, so just enable it in case
 	 * we're going to unload/reload. */
-	intel_display_set_init_power(dev, true);
-	intel_power_domains_remove(dev);
+	intel_display_set_init_power(dev_priv, true);
+	intel_power_domains_remove(dev_priv);
 
 	i915_teardown_sysfs(dev);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 2d05d7c..658fe24 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -265,6 +265,7 @@
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 	.has_llc = 1,
 	.has_ddi = 1,
+	.has_fbc = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
 };
 
@@ -274,6 +275,7 @@
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 	.has_llc = 1,
 	.has_ddi = 1,
+	.has_fbc = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
 };
 
@@ -324,7 +326,7 @@
 void intel_detect_pch(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct pci_dev *pch;
+	struct pci_dev *pch = NULL;
 
 	/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
 	 * (which really amounts to a PCH but no South Display).
@@ -345,12 +347,9 @@
 	 * all the ISA bridge devices and check for the first match, instead
 	 * of only checking the first one.
 	 */
-	pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
-	while (pch) {
-		struct pci_dev *curr = pch;
+	while ((pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, pch))) {
 		if (pch->vendor == PCI_VENDOR_ID_INTEL) {
-			unsigned short id;
-			id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
+			unsigned short id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
 			dev_priv->pch_id = id;
 
 			if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) {
@@ -382,18 +381,16 @@
 				DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
 				WARN_ON(!IS_HASWELL(dev));
 				WARN_ON(!IS_ULT(dev));
-			} else {
-				goto check_next;
-			}
-			pci_dev_put(pch);
+			} else
+				continue;
+
 			break;
 		}
-check_next:
-		pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, curr);
-		pci_dev_put(curr);
 	}
 	if (!pch)
-		DRM_DEBUG_KMS("No PCH found?\n");
+		DRM_DEBUG_KMS("No PCH found.\n");
+
+	pci_dev_put(pch);
 }
 
 bool i915_semaphore_is_enabled(struct drm_device *dev)
@@ -401,15 +398,13 @@
 	if (INTEL_INFO(dev)->gen < 6)
 		return false;
 
-	/* Until we get further testing... */
-	if (IS_GEN8(dev)) {
-		WARN_ON(!i915.preliminary_hw_support);
-		return false;
-	}
-
 	if (i915.semaphores >= 0)
 		return i915.semaphores;
 
+	/* Until we get further testing... */
+	if (IS_GEN8(dev))
+		return false;
+
 #ifdef CONFIG_INTEL_IOMMU
 	/* Enable semaphores on SNB when IO remapping is off */
 	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped)
@@ -434,7 +429,7 @@
 	/* We do a lot of poking in a lot of registers, make sure they work
 	 * properly. */
 	hsw_disable_package_c8(dev_priv);
-	intel_display_set_init_power(dev, true);
+	intel_display_set_init_power(dev_priv, true);
 
 	drm_kms_helper_poll_disable(dev);
 
@@ -477,6 +472,8 @@
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED);
 	console_unlock();
 
+	dev_priv->suspend_count++;
+
 	return 0;
 }
 
@@ -556,7 +553,7 @@
 		mutex_unlock(&dev->struct_mutex);
 	}
 
-	intel_power_domains_init_hw(dev);
+	intel_power_domains_init_hw(dev_priv);
 
 	i915_restore_state(dev);
 	intel_opregion_setup(dev);
@@ -847,6 +844,7 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	WARN_ON(!HAS_RUNTIME_PM(dev));
+	assert_force_wake_inactive(dev_priv);
 
 	DRM_DEBUG_KMS("Suspending device\n");
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9d8ca2a..2a319ba 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -79,7 +79,7 @@
 };
 #define plane_name(p) ((p) + 'A')
 
-#define sprite_name(p, s) ((p) * dev_priv->num_plane + (s) + 'A')
+#define sprite_name(p, s) ((p) * INTEL_INFO(dev)->num_sprites[(p)] + (s) + 'A')
 
 enum port {
 	PORT_A = 0,
@@ -114,6 +114,17 @@
 	POWER_DOMAIN_TRANSCODER_B,
 	POWER_DOMAIN_TRANSCODER_C,
 	POWER_DOMAIN_TRANSCODER_EDP,
+	POWER_DOMAIN_PORT_DDI_A_2_LANES,
+	POWER_DOMAIN_PORT_DDI_A_4_LANES,
+	POWER_DOMAIN_PORT_DDI_B_2_LANES,
+	POWER_DOMAIN_PORT_DDI_B_4_LANES,
+	POWER_DOMAIN_PORT_DDI_C_2_LANES,
+	POWER_DOMAIN_PORT_DDI_C_4_LANES,
+	POWER_DOMAIN_PORT_DDI_D_2_LANES,
+	POWER_DOMAIN_PORT_DDI_D_4_LANES,
+	POWER_DOMAIN_PORT_DSI,
+	POWER_DOMAIN_PORT_CRT,
+	POWER_DOMAIN_PORT_OTHER,
 	POWER_DOMAIN_VGA,
 	POWER_DOMAIN_AUDIO,
 	POWER_DOMAIN_INIT,
@@ -121,8 +132,6 @@
 	POWER_DOMAIN_NUM,
 };
 
-#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1)
-
 #define POWER_DOMAIN_PIPE(pipe) ((pipe) + POWER_DOMAIN_PIPE_A)
 #define POWER_DOMAIN_PIPE_PANEL_FITTER(pipe) \
 		((pipe) + POWER_DOMAIN_PIPE_A_PANEL_FITTER)
@@ -130,14 +139,6 @@
 	((tran) == TRANSCODER_EDP ? POWER_DOMAIN_TRANSCODER_EDP : \
 	 (tran) + POWER_DOMAIN_TRANSCODER_A)
 
-#define HSW_ALWAYS_ON_POWER_DOMAINS (		\
-	BIT(POWER_DOMAIN_PIPE_A) |		\
-	BIT(POWER_DOMAIN_TRANSCODER_EDP))
-#define BDW_ALWAYS_ON_POWER_DOMAINS (		\
-	BIT(POWER_DOMAIN_PIPE_A) |		\
-	BIT(POWER_DOMAIN_TRANSCODER_EDP) |	\
-	BIT(POWER_DOMAIN_PIPE_A_PANEL_FITTER))
-
 enum hpd_pin {
 	HPD_NONE = 0,
 	HPD_PORT_A = HPD_NONE, /* PORT_A is internal */
@@ -159,11 +160,16 @@
 	 I915_GEM_DOMAIN_VERTEX)
 
 #define for_each_pipe(p) for ((p) = 0; (p) < INTEL_INFO(dev)->num_pipes; (p)++)
+#define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++)
 
 #define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \
 	list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
 		if ((intel_encoder)->base.crtc == (__crtc))
 
+#define for_each_connector_on_encoder(dev, __encoder, intel_connector) \
+	list_for_each_entry((intel_connector), &(dev)->mode_config.connector_list, base.head) \
+		if ((intel_connector)->base.encoder == (__encoder))
+
 struct drm_i915_private;
 
 enum intel_dpll_id {
@@ -299,6 +305,10 @@
 	struct kref ref;
 	struct timeval time;
 
+	char error_msg[128];
+	u32 reset_count;
+	u32 suspend_count;
+
 	/* Generic register state */
 	u32 eir;
 	u32 pgtbl_er;
@@ -356,7 +366,7 @@
 			int page_count;
 			u32 gtt_offset;
 			u32 *pages[0];
-		} *ringbuffer, *batchbuffer, *ctx, *hws_page;
+		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
 
 		struct drm_i915_error_request {
 			long jiffies;
@@ -371,6 +381,9 @@
 				u32 pp_dir_base;
 			};
 		} vm_info;
+
+		pid_t pid;
+		char comm[TASK_COMM_LEN];
 	} ring[I915_NUM_RINGS];
 	struct drm_i915_error_buffer {
 		u32 size;
@@ -495,7 +508,7 @@
 	unsigned fw_rendercount;
 	unsigned fw_mediacount;
 
-	struct delayed_work force_wake_work;
+	struct timer_list force_wake_timer;
 };
 
 #define DEV_INFO_FOR_EACH_FLAG(func, sep) \
@@ -530,6 +543,7 @@
 struct intel_device_info {
 	u32 display_mmio_offset;
 	u8 num_pipes:3;
+	u8 num_sprites[I915_MAX_PIPES];
 	u8 gen;
 	u8 ring_mask; /* Rings supported by the HW */
 	DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG, SEP_SEMICOLON);
@@ -647,12 +661,12 @@
 				     enum i915_cache_level level,
 				     bool valid); /* Create a valid PTE */
 	void (*clear_range)(struct i915_address_space *vm,
-			    unsigned int first_entry,
-			    unsigned int num_entries,
+			    uint64_t start,
+			    uint64_t length,
 			    bool use_scratch);
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
-			       unsigned int first_entry,
+			       uint64_t start,
 			       enum i915_cache_level cache_level);
 	void (*cleanup)(struct i915_address_space *vm);
 };
@@ -686,21 +700,21 @@
 };
 #define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
 
+#define GEN8_LEGACY_PDPS 4
 struct i915_hw_ppgtt {
 	struct i915_address_space base;
 	struct kref ref;
 	struct drm_mm_node node;
 	unsigned num_pd_entries;
+	unsigned num_pd_pages; /* gen8+ */
 	union {
 		struct page **pt_pages;
-		struct page *gen8_pt_pages;
+		struct page **gen8_pt_pages[GEN8_LEGACY_PDPS];
 	};
 	struct page *pd_pages;
-	int num_pd_pages;
-	int num_pt_pages;
 	union {
 		uint32_t pd_offset;
-		dma_addr_t pd_dma_addr[4];
+		dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS];
 	};
 	union {
 		dma_addr_t *pt_dma_addr;
@@ -1011,6 +1025,36 @@
 	struct drm_i915_gem_object *renderctx;
 };
 
+struct drm_i915_private;
+struct i915_power_well;
+
+struct i915_power_well_ops {
+	/*
+	 * Synchronize the well's hw state to match the current sw state, for
+	 * example enable/disable it based on the current refcount. Called
+	 * during driver init and resume time, possibly after first calling
+	 * the enable/disable handlers.
+	 */
+	void (*sync_hw)(struct drm_i915_private *dev_priv,
+			struct i915_power_well *power_well);
+	/*
+	 * Enable the well and resources that depend on it (for example
+	 * interrupts located on the well). Called after the 0->1 refcount
+	 * transition.
+	 */
+	void (*enable)(struct drm_i915_private *dev_priv,
+		       struct i915_power_well *power_well);
+	/*
+	 * Disable the well and resources that depend on it. Called after
+	 * the 1->0 refcount transition.
+	 */
+	void (*disable)(struct drm_i915_private *dev_priv,
+			struct i915_power_well *power_well);
+	/* Returns the hw enabled state. */
+	bool (*is_enabled)(struct drm_i915_private *dev_priv,
+			   struct i915_power_well *power_well);
+};
+
 /* Power well structure for haswell */
 struct i915_power_well {
 	const char *name;
@@ -1018,11 +1062,8 @@
 	/* power well enable/disable usage count */
 	int count;
 	unsigned long domains;
-	void *data;
-	void (*set)(struct drm_device *dev, struct i915_power_well *power_well,
-		    bool enable);
-	bool (*is_enabled)(struct drm_device *dev,
-			   struct i915_power_well *power_well);
+	unsigned long data;
+	const struct i915_power_well_ops *ops;
 };
 
 struct i915_power_domains {
@@ -1119,6 +1160,14 @@
 	 */
 	bool interruptible;
 
+	/**
+	 * Is the GPU currently considered idle, or busy executing userspace
+	 * requests?  Whilst idle, we attempt to power down the hardware and
+	 * display clocks. In order to reduce the effect on performance, there
+	 * is a slight delay before we do so.
+	 */
+	bool busy;
+
 	/** Bit 6 swizzling required for X tiling */
 	uint32_t bit_6_swizzle_x;
 	/** Bit 6 swizzling required for Y tiling */
@@ -1308,11 +1357,10 @@
  * Ideally every piece of our code that needs PC8+ disabled would call
  * hsw_disable_package_c8, which would increment disable_count and prevent the
  * system from reaching PC8+. But we don't have a symmetric way to do this for
- * everything, so we have the requirements_met and gpu_idle variables. When we
- * switch requirements_met or gpu_idle to true we decrease disable_count, and
- * increase it in the opposite case. The requirements_met variable is true when
- * all the CRTCs, encoders and the power well are disabled. The gpu_idle
- * variable is true when the GPU is idle.
+ * everything, so we have the requirements_met variable. When we switch
+ * requirements_met to true we decrease disable_count, and increase it in the
+ * opposite case. The requirements_met variable is true when all the CRTCs,
+ * encoders and the power well are disabled.
  *
  * In addition to everything, we only actually enable PC8+ if disable_count
  * stays at zero for at least some seconds. This is implemented with the
@@ -1335,7 +1383,6 @@
  */
 struct i915_package_c8 {
 	bool requirements_met;
-	bool gpu_idle;
 	bool irqs_disabled;
 	/* Only true after the delayed work task actually enables it. */
 	bool enabled;
@@ -1390,7 +1437,7 @@
 	struct drm_device *dev;
 	struct kmem_cache *slab;
 
-	const struct intel_device_info *info;
+	const struct intel_device_info info;
 
 	int relative_constants_mode;
 
@@ -1422,6 +1469,8 @@
 	/* protects the irq masks */
 	spinlock_t irq_lock;
 
+	bool display_irqs_enabled;
+
 	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
 	struct pm_qos_request pm_qos;
 
@@ -1435,6 +1484,7 @@
 	};
 	u32 gt_irq_mask;
 	u32 pm_irq_mask;
+	u32 pipestat_irq_mask[I915_MAX_PIPES];
 
 	struct work_struct hotplug_work;
 	bool enable_hotplug_processing;
@@ -1450,8 +1500,6 @@
 	u32 hpd_event_bits;
 	struct timer_list hotplug_reenable_timer;
 
-	int num_plane;
-
 	struct i915_fbc fbc;
 	struct intel_opregion opregion;
 	struct intel_vbt_data vbt;
@@ -1501,8 +1549,8 @@
 
 	struct sdvo_device_mapping sdvo_mappings[2];
 
-	struct drm_crtc *plane_to_crtc_mapping[3];
-	struct drm_crtc *pipe_to_crtc_mapping[3];
+	struct drm_crtc *plane_to_crtc_mapping[I915_MAX_PIPES];
+	struct drm_crtc *pipe_to_crtc_mapping[I915_MAX_PIPES];
 	wait_queue_head_t pending_flip_queue;
 
 #ifdef CONFIG_DEBUG_FS
@@ -1590,6 +1638,8 @@
 	struct i915_dri1_state dri1;
 	/* Old ums support infrastructure, same warning applies. */
 	struct i915_ums_state ums;
+
+	u32 suspend_count;
 } drm_i915_private_t;
 
 static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
@@ -1741,7 +1791,6 @@
 	/** for phy allocated objects */
 	struct drm_i915_gem_phys_object *phys_obj;
 };
-#define to_gem_object(obj) (&((struct drm_i915_gem_object *)(obj))->base)
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
@@ -1787,6 +1836,7 @@
 
 struct drm_i915_file_private {
 	struct drm_i915_private *dev_priv;
+	struct drm_file *file;
 
 	struct {
 		spinlock_t lock;
@@ -1799,7 +1849,91 @@
 	atomic_t rps_wait_boost;
 };
 
-#define INTEL_INFO(dev)	(to_i915(dev)->info)
+/*
+ * A command that requires special handling by the command parser.
+ */
+struct drm_i915_cmd_descriptor {
+	/*
+	 * Flags describing how the command parser processes the command.
+	 *
+	 * CMD_DESC_FIXED: The command has a fixed length if this is set,
+	 *                 a length mask if not set
+	 * CMD_DESC_SKIP: The command is allowed but does not follow the
+	 *                standard length encoding for the opcode range in
+	 *                which it falls
+	 * CMD_DESC_REJECT: The command is never allowed
+	 * CMD_DESC_REGISTER: The command should be checked against the
+	 *                    register whitelist for the appropriate ring
+	 * CMD_DESC_MASTER: The command is allowed if the submitting process
+	 *                  is the DRM master
+	 */
+	u32 flags;
+#define CMD_DESC_FIXED    (1<<0)
+#define CMD_DESC_SKIP     (1<<1)
+#define CMD_DESC_REJECT   (1<<2)
+#define CMD_DESC_REGISTER (1<<3)
+#define CMD_DESC_BITMASK  (1<<4)
+#define CMD_DESC_MASTER   (1<<5)
+
+	/*
+	 * The command's unique identification bits and the bitmask to get them.
+	 * This isn't strictly the opcode field as defined in the spec and may
+	 * also include type, subtype, and/or subop fields.
+	 */
+	struct {
+		u32 value;
+		u32 mask;
+	} cmd;
+
+	/*
+	 * The command's length. The command is either fixed length (i.e. does
+	 * not include a length field) or has a length field mask. The flag
+	 * CMD_DESC_FIXED indicates a fixed length. Otherwise, the command has
+	 * a length mask. All command entries in a command table must include
+	 * length information.
+	 */
+	union {
+		u32 fixed;
+		u32 mask;
+	} length;
+
+	/*
+	 * Describes where to find a register address in the command to check
+	 * against the ring's register whitelist. Only valid if flags has the
+	 * CMD_DESC_REGISTER bit set.
+	 */
+	struct {
+		u32 offset;
+		u32 mask;
+	} reg;
+
+#define MAX_CMD_DESC_BITMASKS 3
+	/*
+	 * Describes command checks where a particular dword is masked and
+	 * compared against an expected value. If the command does not match
+	 * the expected value, the parser rejects it. Only valid if flags has
+	 * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero
+	 * are valid.
+	 */
+	struct {
+		u32 offset;
+		u32 mask;
+		u32 expected;
+	} bits[MAX_CMD_DESC_BITMASKS];
+};
+
+/*
+ * A table of commands requiring special handling by the command parser.
+ *
+ * Each ring has an array of tables. Each table consists of an array of command
+ * descriptors, which must be sorted with command opcodes in ascending order.
+ */
+struct drm_i915_cmd_table {
+	const struct drm_i915_cmd_descriptor *table;
+	int count;
+};
+
+#define INTEL_INFO(dev)	(&to_i915(dev)->info)
 
 #define IS_I830(dev)		((dev)->pdev->device == 0x3577)
 #define IS_845G(dev)		((dev)->pdev->device == 0x2562)
@@ -1953,18 +2087,21 @@
 	int vbt_sdvo_panel_type;
 	int enable_rc6;
 	int enable_fbc;
-	bool enable_hangcheck;
 	int enable_ppgtt;
 	int enable_psr;
 	unsigned int preliminary_hw_support;
 	int disable_power_well;
 	int enable_ips;
-	bool fastboot;
 	int enable_pc8;
 	int pc8_timeout;
+	int invert_brightness;
+	int enable_cmd_parser;
+	/* leave bools at the end to not create holes */
+	bool enable_hangcheck;
+	bool fastboot;
 	bool prefault_disable;
 	bool reset;
-	int invert_brightness;
+	bool disable_display;
 };
 extern struct i915_params i915 __read_mostly;
 
@@ -1998,7 +2135,9 @@
 
 /* i915_irq.c */
 void i915_queue_hangcheck(struct drm_device *dev);
-void i915_handle_error(struct drm_device *dev, bool wedged);
+__printf(3, 4)
+void i915_handle_error(struct drm_device *dev, bool wedged,
+		       const char *fmt, ...);
 
 void gen6_set_pm_mask(struct drm_i915_private *dev_priv, u32 pm_iir,
 							int new_delay);
@@ -2012,10 +2151,15 @@
 extern void intel_uncore_fini(struct drm_device *dev);
 
 void
-i915_enable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe, u32 mask);
+i915_enable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe,
+		     u32 status_mask);
 
 void
-i915_disable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe, u32 mask);
+i915_disable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe,
+		      u32 status_mask);
+
+void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv);
+void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv);
 
 /* i915_gem.c */
 int i915_gem_init_ioctl(struct drm_device *dev, void *data,
@@ -2076,19 +2220,22 @@
 void i915_gem_free_object(struct drm_gem_object *obj);
 void i915_gem_vma_destroy(struct i915_vma *vma);
 
+#define PIN_MAPPABLE 0x1
+#define PIN_NONBLOCK 0x2
+#define PIN_GLOBAL 0x4
 int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,
 				     struct i915_address_space *vm,
 				     uint32_t alignment,
-				     bool map_and_fenceable,
-				     bool nonblocking);
-void i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj);
+				     unsigned flags);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
-int __must_check i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj);
 int i915_gem_object_put_pages(struct drm_i915_gem_object *obj);
 void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv);
 void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
 void i915_gem_lastclose(struct drm_device *dev);
 
+int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
+				    int *needs_clflush);
+
 int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
 static inline struct page *i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
 {
@@ -2155,8 +2302,10 @@
 	}
 }
 
+struct drm_i915_gem_request *
+i915_gem_find_active_request(struct intel_ring_buffer *ring);
+
 bool i915_gem_retire_requests(struct drm_device *dev);
-void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring);
 int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
 				      bool interruptible);
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
@@ -2283,13 +2432,19 @@
 static inline int __must_check
 i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
 		      uint32_t alignment,
-		      bool map_and_fenceable,
-		      bool nonblocking)
+		      unsigned flags)
 {
-	return i915_gem_object_pin(obj, obj_to_ggtt(obj), alignment,
-				   map_and_fenceable, nonblocking);
+	return i915_gem_object_pin(obj, obj_to_ggtt(obj), alignment, flags | PIN_GLOBAL);
 }
 
+static inline int
+i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj)
+{
+	return i915_vma_unbind(i915_gem_obj_to_ggtt(obj));
+}
+
+void i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj);
+
 /* i915_gem_context.c */
 #define ctx_to_ppgtt(ctx) container_of((ctx)->vm, struct i915_hw_ppgtt, base)
 int __must_check i915_gem_context_init(struct drm_device *dev);
@@ -2331,8 +2486,7 @@
 					  int min_size,
 					  unsigned alignment,
 					  unsigned cache_level,
-					  bool mappable,
-					  bool nonblock);
+					  unsigned flags);
 int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 int i915_gem_evict_everything(struct drm_device *dev);
 
@@ -2352,63 +2506,7 @@
 		intel_gtt_chipset_flush();
 }
 int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
-static inline bool intel_enable_ppgtt(struct drm_device *dev, bool full)
-{
-	if (i915.enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
-		return false;
-
-	if (i915.enable_ppgtt == 1 && full)
-		return false;
-
-#ifdef CONFIG_INTEL_IOMMU
-	/* Disable ppgtt on SNB if VT-d is on. */
-	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
-		DRM_INFO("Disabling PPGTT because VT-d is on\n");
-		return false;
-	}
-#endif
-
-	if (full)
-		return HAS_PPGTT(dev);
-	else
-		return HAS_ALIASING_PPGTT(dev);
-}
-
-static inline void ppgtt_release(struct kref *kref)
-{
-	struct i915_hw_ppgtt *ppgtt = container_of(kref, struct i915_hw_ppgtt, ref);
-	struct drm_device *dev = ppgtt->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_address_space *vm = &ppgtt->base;
-
-	if (ppgtt == dev_priv->mm.aliasing_ppgtt ||
-	    (list_empty(&vm->active_list) && list_empty(&vm->inactive_list))) {
-		ppgtt->base.cleanup(&ppgtt->base);
-		return;
-	}
-
-	/*
-	 * Make sure vmas are unbound before we take down the drm_mm
-	 *
-	 * FIXME: Proper refcounting should take care of this, this shouldn't be
-	 * needed at all.
-	 */
-	if (!list_empty(&vm->active_list)) {
-		struct i915_vma *vma;
-
-		list_for_each_entry(vma, &vm->active_list, mm_list)
-			if (WARN_ON(list_empty(&vma->vma_link) ||
-				    list_is_singular(&vma->vma_link)))
-				break;
-
-		i915_gem_evict_vm(&ppgtt->base, true);
-	} else {
-		i915_gem_retire_requests(dev);
-		i915_gem_evict_vm(&ppgtt->base, false);
-	}
-
-	ppgtt->base.cleanup(&ppgtt->base);
-}
+bool intel_enable_ppgtt(struct drm_device *dev, bool full);
 
 /* i915_gem_stolen.c */
 int i915_gem_init_stolen(struct drm_device *dev);
@@ -2465,7 +2563,8 @@
 {
 	kfree(eb->buf);
 }
-void i915_capture_error_state(struct drm_device *dev);
+void i915_capture_error_state(struct drm_device *dev, bool wedge,
+			      const char *error_msg);
 void i915_error_state_get(struct drm_device *dev,
 			  struct i915_error_state_file_priv *error_priv);
 void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
@@ -2474,6 +2573,14 @@
 void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
 const char *i915_cache_level_str(int type);
 
+/* i915_cmd_parser.c */
+void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring);
+bool i915_needs_cmd_parser(struct intel_ring_buffer *ring);
+int i915_parse_cmds(struct intel_ring_buffer *ring,
+		    struct drm_i915_gem_object *batch_obj,
+		    u32 batch_start_offset,
+		    bool is_master);
+
 /* i915_suspend.c */
 extern int i915_save_state(struct drm_device *dev);
 extern int i915_restore_state(struct drm_device *dev);
@@ -2547,10 +2654,12 @@
 extern void intel_modeset_init(struct drm_device *dev);
 extern void intel_modeset_gem_init(struct drm_device *dev);
 extern void intel_modeset_cleanup(struct drm_device *dev);
+extern void intel_connector_unregister(struct intel_connector *);
 extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state);
 extern void intel_modeset_setup_hw_state(struct drm_device *dev,
 					 bool force_restore);
 extern void i915_redisable_vga(struct drm_device *dev);
+extern void i915_redisable_vga_power_on(struct drm_device *dev);
 extern bool intel_fbc_enabled(struct drm_device *dev);
 extern void intel_disable_fbc(struct drm_device *dev);
 extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
@@ -2585,6 +2694,7 @@
  */
 void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine);
 void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine);
+void assert_force_wake_inactive(struct drm_i915_private *dev_priv);
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a8a069f..9c52f68 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -43,12 +43,6 @@
 static __must_check int
 i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
 			       bool readonly);
-static __must_check int
-i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
-			   struct i915_address_space *vm,
-			   unsigned alignment,
-			   bool map_and_fenceable,
-			   bool nonblocking);
 static int i915_gem_phys_pwrite(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				struct drm_i915_gem_pwrite *args,
@@ -67,6 +61,7 @@
 static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
 static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
+static void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring);
 
 static bool cpu_cache_is_coherent(struct drm_device *dev,
 				  enum i915_cache_level level)
@@ -332,6 +327,42 @@
 	return 0;
 }
 
+/*
+ * Pins the specified object's pages and synchronizes the object with
+ * GPU accesses. Sets needs_clflush to non-zero if the caller should
+ * flush the object from the CPU cache.
+ */
+int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
+				    int *needs_clflush)
+{
+	int ret;
+
+	*needs_clflush = 0;
+
+	if (!obj->base.filp)
+		return -EINVAL;
+
+	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)) {
+		/* If we're not in the cpu read domain, set ourself into the gtt
+		 * read domain and manually flush cachelines (if required). This
+		 * optimizes for the case when the gpu will dirty the data
+		 * anyway again before the next pread happens. */
+		*needs_clflush = !cpu_cache_is_coherent(obj->base.dev,
+							obj->cache_level);
+		ret = i915_gem_object_wait_rendering(obj, true);
+		if (ret)
+			return ret;
+	}
+
+	ret = i915_gem_object_get_pages(obj);
+	if (ret)
+		return ret;
+
+	i915_gem_object_pin_pages(obj);
+
+	return ret;
+}
+
 /* Per-page copy function for the shmem pread fastpath.
  * Flushes invalid cachelines before reading the target if
  * needs_clflush is set. */
@@ -429,23 +460,10 @@
 
 	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
 
-	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)) {
-		/* If we're not in the cpu read domain, set ourself into the gtt
-		 * read domain and manually flush cachelines (if required). This
-		 * optimizes for the case when the gpu will dirty the data
-		 * anyway again before the next pread happens. */
-		needs_clflush = !cpu_cache_is_coherent(dev, obj->cache_level);
-		ret = i915_gem_object_wait_rendering(obj, true);
-		if (ret)
-			return ret;
-	}
-
-	ret = i915_gem_object_get_pages(obj);
+	ret = i915_gem_obj_prepare_shmem_read(obj, &needs_clflush);
 	if (ret)
 		return ret;
 
-	i915_gem_object_pin_pages(obj);
-
 	offset = args->offset;
 
 	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents,
@@ -605,7 +623,7 @@
 	char __user *user_data;
 	int page_offset, page_length, ret;
 
-	ret = i915_gem_obj_ggtt_pin(obj, 0, true, true);
+	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK);
 	if (ret)
 		goto out;
 
@@ -1014,7 +1032,8 @@
 			struct timespec *timeout,
 			struct drm_i915_file_private *file_priv)
 {
-	drm_i915_private_t *dev_priv = ring->dev->dev_private;
+	struct drm_device *dev = ring->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
 	const bool irq_test_in_progress =
 		ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring);
 	struct timespec before, now;
@@ -1029,7 +1048,7 @@
 
 	timeout_expire = timeout ? jiffies + timespec_to_jiffies_timeout(timeout) : 0;
 
-	if (dev_priv->info->gen >= 6 && can_wait_boost(file_priv)) {
+	if (INTEL_INFO(dev)->gen >= 6 && can_wait_boost(file_priv)) {
 		gen6_rps_boost(dev_priv);
 		if (file_priv)
 			mod_delayed_work(dev_priv->wq,
@@ -1184,7 +1203,7 @@
  */
 static __must_check int
 i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
-					    struct drm_file *file,
+					    struct drm_i915_file_private *file_priv,
 					    bool readonly)
 {
 	struct drm_device *dev = obj->base.dev;
@@ -1211,7 +1230,7 @@
 
 	reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
 	mutex_unlock(&dev->struct_mutex);
-	ret = __wait_seqno(ring, seqno, reset_counter, true, NULL, file->driver_priv);
+	ret = __wait_seqno(ring, seqno, reset_counter, true, NULL, file_priv);
 	mutex_lock(&dev->struct_mutex);
 	if (ret)
 		return ret;
@@ -1260,7 +1279,9 @@
 	 * We will repeat the flush holding the lock in the normal manner
 	 * to catch cases where we are gazumped.
 	 */
-	ret = i915_gem_object_wait_rendering__nonblocking(obj, file, !write_domain);
+	ret = i915_gem_object_wait_rendering__nonblocking(obj,
+							  file->driver_priv,
+							  !write_domain);
 	if (ret)
 		goto unref;
 
@@ -1392,6 +1413,15 @@
 
 	trace_i915_gem_object_fault(obj, page_offset, true, write);
 
+	/* Try to flush the object off the GPU first without holding the lock.
+	 * Upon reacquiring the lock, we will perform our sanity checks and then
+	 * repeat the flush holding the lock in the normal manner to catch cases
+	 * where we are gazumped.
+	 */
+	ret = i915_gem_object_wait_rendering__nonblocking(obj, NULL, !write);
+	if (ret)
+		goto unlock;
+
 	/* Access to snoopable pages through the GTT is incoherent. */
 	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(dev)) {
 		ret = -EINVAL;
@@ -1399,7 +1429,7 @@
 	}
 
 	/* Now bind it into the GTT if needed */
-	ret = i915_gem_obj_ggtt_pin(obj,  0, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE);
 	if (ret)
 		goto unlock;
 
@@ -1502,7 +1532,8 @@
 	if (!obj->fault_mappable)
 		return;
 
-	drm_vma_node_unmap(&obj->base.vma_node, obj->base.dev->dev_mapping);
+	drm_vma_node_unmap(&obj->base.vma_node,
+			   obj->base.dev->anon_inode->i_mapping);
 	obj->fault_mappable = false;
 }
 
@@ -1618,7 +1649,7 @@
 	}
 
 	if (obj->madv != I915_MADV_WILLNEED) {
-		DRM_ERROR("Attempting to mmap a purgeable buffer\n");
+		DRM_DEBUG("Attempting to mmap a purgeable buffer\n");
 		ret = -EFAULT;
 		goto out;
 	}
@@ -1972,7 +2003,7 @@
 		return 0;
 
 	if (obj->madv != I915_MADV_WILLNEED) {
-		DRM_ERROR("Attempting to obtain a purgeable object\n");
+		DRM_DEBUG("Attempting to obtain a purgeable object\n");
 		return -EFAULT;
 	}
 
@@ -2142,7 +2173,6 @@
 	drm_i915_private_t *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *request;
 	u32 request_ring_position, request_start;
-	int was_empty;
 	int ret;
 
 	request_start = intel_ring_get_tail(ring);
@@ -2193,7 +2223,6 @@
 		i915_gem_context_reference(request->ctx);
 
 	request->emitted_jiffies = jiffies;
-	was_empty = list_empty(&ring->request_list);
 	list_add_tail(&request->list, &ring->request_list);
 	request->file_priv = NULL;
 
@@ -2214,13 +2243,11 @@
 	if (!dev_priv->ums.mm_suspended) {
 		i915_queue_hangcheck(ring->dev);
 
-		if (was_empty) {
-			cancel_delayed_work_sync(&dev_priv->mm.idle_work);
-			queue_delayed_work(dev_priv->wq,
-					   &dev_priv->mm.retire_work,
-					   round_jiffies_up_relative(HZ));
-			intel_mark_busy(dev_priv->dev);
-		}
+		cancel_delayed_work_sync(&dev_priv->mm.idle_work);
+		queue_delayed_work(dev_priv->wq,
+				   &dev_priv->mm.retire_work,
+				   round_jiffies_up_relative(HZ));
+		intel_mark_busy(dev_priv->dev);
 	}
 
 	if (out_seqno)
@@ -2253,14 +2280,13 @@
 		return true;
 
 	if (elapsed <= DRM_I915_CTX_BAN_PERIOD) {
-		if (dev_priv->gpu_error.stop_rings == 0 &&
-		    i915_gem_context_is_default(ctx)) {
-			DRM_ERROR("gpu hanging too fast, banning!\n");
-		} else {
+		if (!i915_gem_context_is_default(ctx)) {
 			DRM_DEBUG("context hanging too fast, banning!\n");
+			return true;
+		} else if (dev_priv->gpu_error.stop_rings == 0) {
+			DRM_ERROR("gpu hanging too fast, banning!\n");
+			return true;
 		}
-
-		return true;
 	}
 
 	return false;
@@ -2297,11 +2323,13 @@
 	kfree(request);
 }
 
-static struct drm_i915_gem_request *
-i915_gem_find_first_non_complete(struct intel_ring_buffer *ring)
+struct drm_i915_gem_request *
+i915_gem_find_active_request(struct intel_ring_buffer *ring)
 {
 	struct drm_i915_gem_request *request;
-	const u32 completed_seqno = ring->get_seqno(ring, false);
+	u32 completed_seqno;
+
+	completed_seqno = ring->get_seqno(ring, false);
 
 	list_for_each_entry(request, &ring->request_list, list) {
 		if (i915_seqno_passed(completed_seqno, request->seqno))
@@ -2319,7 +2347,7 @@
 	struct drm_i915_gem_request *request;
 	bool ring_hung;
 
-	request = i915_gem_find_first_non_complete(ring);
+	request = i915_gem_find_active_request(ring);
 
 	if (request == NULL)
 		return;
@@ -2411,7 +2439,7 @@
 /**
  * This function clears the request list as sequence numbers are passed.
  */
-void
+static void
 i915_gem_retire_requests_ring(struct intel_ring_buffer *ring)
 {
 	uint32_t seqno;
@@ -2709,7 +2737,6 @@
 
 	if (!drm_mm_node_allocated(&vma->node)) {
 		i915_gem_vma_destroy(vma);
-
 		return 0;
 	}
 
@@ -2739,7 +2766,7 @@
 
 	i915_gem_gtt_finish_object(obj);
 
-	list_del(&vma->mm_list);
+	list_del_init(&vma->mm_list);
 	/* Avoid an unnecessary call to unbind on rebind. */
 	if (i915_is_ggtt(vma->vm))
 		obj->map_and_fenceable = true;
@@ -2761,26 +2788,6 @@
 	return 0;
 }
 
-/**
- * Unbinds an object from the global GTT aperture.
- */
-int
-i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj)
-{
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
-	struct i915_address_space *ggtt = &dev_priv->gtt.base;
-
-	if (!i915_gem_obj_ggtt_bound(obj))
-		return 0;
-
-	if (i915_gem_obj_to_ggtt(obj)->pin_count)
-		return -EBUSY;
-
-	BUG_ON(obj->pages == NULL);
-
-	return i915_vma_unbind(i915_gem_obj_to_vma(obj, ggtt));
-}
-
 int i915_gpu_idle(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -3203,18 +3210,17 @@
 /**
  * Finds free space in the GTT aperture and binds the object there.
  */
-static int
+static struct i915_vma *
 i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 			   struct i915_address_space *vm,
 			   unsigned alignment,
-			   bool map_and_fenceable,
-			   bool nonblocking)
+			   unsigned flags)
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
 	size_t gtt_max =
-		map_and_fenceable ? dev_priv->gtt.mappable_end : vm->total;
+		flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total;
 	struct i915_vma *vma;
 	int ret;
 
@@ -3226,41 +3232,39 @@
 						     obj->tiling_mode, true);
 	unfenced_alignment =
 		i915_gem_get_gtt_alignment(dev,
-						    obj->base.size,
-						    obj->tiling_mode, false);
+					   obj->base.size,
+					   obj->tiling_mode, false);
 
 	if (alignment == 0)
-		alignment = map_and_fenceable ? fence_alignment :
+		alignment = flags & PIN_MAPPABLE ? fence_alignment :
 						unfenced_alignment;
-	if (map_and_fenceable && alignment & (fence_alignment - 1)) {
-		DRM_ERROR("Invalid object alignment requested %u\n", alignment);
-		return -EINVAL;
+	if (flags & PIN_MAPPABLE && alignment & (fence_alignment - 1)) {
+		DRM_DEBUG("Invalid object alignment requested %u\n", alignment);
+		return ERR_PTR(-EINVAL);
 	}
 
-	size = map_and_fenceable ? fence_size : obj->base.size;
+	size = flags & PIN_MAPPABLE ? fence_size : obj->base.size;
 
 	/* If the object is bigger than the entire aperture, reject it early
 	 * before evicting everything in a vain attempt to find space.
 	 */
 	if (obj->base.size > gtt_max) {
-		DRM_ERROR("Attempting to bind an object larger than the aperture: object=%zd > %s aperture=%zu\n",
+		DRM_DEBUG("Attempting to bind an object larger than the aperture: object=%zd > %s aperture=%zu\n",
 			  obj->base.size,
-			  map_and_fenceable ? "mappable" : "total",
+			  flags & PIN_MAPPABLE ? "mappable" : "total",
 			  gtt_max);
-		return -E2BIG;
+		return ERR_PTR(-E2BIG);
 	}
 
 	ret = i915_gem_object_get_pages(obj);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	i915_gem_object_pin_pages(obj);
 
 	vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
+	if (IS_ERR(vma))
 		goto err_unpin;
-	}
 
 search_free:
 	ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
@@ -3269,9 +3273,7 @@
 						  DRM_MM_SEARCH_DEFAULT);
 	if (ret) {
 		ret = i915_gem_evict_something(dev, vm, size, alignment,
-					       obj->cache_level,
-					       map_and_fenceable,
-					       nonblocking);
+					       obj->cache_level, flags);
 		if (ret == 0)
 			goto search_free;
 
@@ -3302,19 +3304,23 @@
 		obj->map_and_fenceable = mappable && fenceable;
 	}
 
-	WARN_ON(map_and_fenceable && !obj->map_and_fenceable);
+	WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable);
 
-	trace_i915_vma_bind(vma, map_and_fenceable);
+	trace_i915_vma_bind(vma, flags);
+	vma->bind_vma(vma, obj->cache_level,
+		      flags & (PIN_MAPPABLE | PIN_GLOBAL) ? GLOBAL_BIND : 0);
+
 	i915_gem_verify_gtt(dev);
-	return 0;
+	return vma;
 
 err_remove_node:
 	drm_mm_remove_node(&vma->node);
 err_free_vma:
 	i915_gem_vma_destroy(vma);
+	vma = ERR_PTR(ret);
 err_unpin:
 	i915_gem_object_unpin_pages(obj);
-	return ret;
+	return vma;
 }
 
 bool
@@ -3506,7 +3512,9 @@
 		}
 
 		list_for_each_entry(vma, &obj->vma_list, vma_link)
-			vma->bind_vma(vma, cache_level, 0);
+			if (drm_mm_node_allocated(&vma->node))
+				vma->bind_vma(vma, cache_level,
+					      obj->has_global_gtt_mapping ? GLOBAL_BIND : 0);
 	}
 
 	list_for_each_entry(vma, &obj->vma_list, vma_link)
@@ -3675,7 +3683,7 @@
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_obj_ggtt_pin(obj, alignment, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, alignment, PIN_MAPPABLE);
 	if (ret)
 		goto err_unpin_display;
 
@@ -3831,52 +3839,49 @@
 i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		    struct i915_address_space *vm,
 		    uint32_t alignment,
-		    bool map_and_fenceable,
-		    bool nonblocking)
+		    unsigned flags)
 {
-	const u32 flags = map_and_fenceable ? GLOBAL_BIND : 0;
 	struct i915_vma *vma;
 	int ret;
 
-	WARN_ON(map_and_fenceable && !i915_is_ggtt(vm));
+	if (WARN_ON(flags & (PIN_GLOBAL | PIN_MAPPABLE) && !i915_is_ggtt(vm)))
+		return -EINVAL;
 
 	vma = i915_gem_obj_to_vma(obj, vm);
-
 	if (vma) {
 		if (WARN_ON(vma->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT))
 			return -EBUSY;
 
 		if ((alignment &&
 		     vma->node.start & (alignment - 1)) ||
-		    (map_and_fenceable && !obj->map_and_fenceable)) {
+		    (flags & PIN_MAPPABLE && !obj->map_and_fenceable)) {
 			WARN(vma->pin_count,
 			     "bo is already pinned with incorrect alignment:"
 			     " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
 			     " obj->map_and_fenceable=%d\n",
 			     i915_gem_obj_offset(obj, vm), alignment,
-			     map_and_fenceable,
+			     flags & PIN_MAPPABLE,
 			     obj->map_and_fenceable);
 			ret = i915_vma_unbind(vma);
 			if (ret)
 				return ret;
+
+			vma = NULL;
 		}
 	}
 
-	if (!i915_gem_obj_bound(obj, vm)) {
-		ret = i915_gem_object_bind_to_vm(obj, vm, alignment,
-						 map_and_fenceable,
-						 nonblocking);
-		if (ret)
-			return ret;
-
+	if (vma == NULL || !drm_mm_node_allocated(&vma->node)) {
+		vma = i915_gem_object_bind_to_vm(obj, vm, alignment, flags);
+		if (IS_ERR(vma))
+			return PTR_ERR(vma);
 	}
 
-	vma = i915_gem_obj_to_vma(obj, vm);
+	if (flags & PIN_GLOBAL && !obj->has_global_gtt_mapping)
+		vma->bind_vma(vma, obj->cache_level, GLOBAL_BIND);
 
-	vma->bind_vma(vma, obj->cache_level, flags);
-
-	i915_gem_obj_to_vma(obj, vm)->pin_count++;
-	obj->pin_mappable |= map_and_fenceable;
+	vma->pin_count++;
+	if (flags & PIN_MAPPABLE)
+		obj->pin_mappable |= true;
 
 	return 0;
 }
@@ -3916,13 +3921,13 @@
 	}
 
 	if (obj->madv != I915_MADV_WILLNEED) {
-		DRM_ERROR("Attempting to pin a purgeable buffer\n");
+		DRM_DEBUG("Attempting to pin a purgeable buffer\n");
 		ret = -EFAULT;
 		goto out;
 	}
 
 	if (obj->pin_filp != NULL && obj->pin_filp != file) {
-		DRM_ERROR("Already pinned in i915_gem_pin_ioctl(): %d\n",
+		DRM_DEBUG("Already pinned in i915_gem_pin_ioctl(): %d\n",
 			  args->handle);
 		ret = -EINVAL;
 		goto out;
@@ -3934,7 +3939,7 @@
 	}
 
 	if (obj->user_pin_count == 0) {
-		ret = i915_gem_obj_ggtt_pin(obj, args->alignment, true, false);
+		ret = i915_gem_obj_ggtt_pin(obj, args->alignment, PIN_MAPPABLE);
 		if (ret)
 			goto out;
 	}
@@ -3969,7 +3974,7 @@
 	}
 
 	if (obj->pin_filp != file) {
-		DRM_ERROR("Not pinned by caller in i915_gem_pin_ioctl(): %d\n",
+		DRM_DEBUG("Not pinned by caller in i915_gem_pin_ioctl(): %d\n",
 			  args->handle);
 		ret = -EINVAL;
 		goto out;
@@ -4877,6 +4882,7 @@
 
 	file->driver_priv = file_priv;
 	file_priv->dev_priv = dev->dev_private;
+	file_priv->file = file;
 
 	spin_lock_init(&file_priv->mm.lock);
 	INIT_LIST_HEAD(&file_priv->mm.request_list);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 19fd362..ce41cff 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -99,6 +99,50 @@
 static int do_switch(struct intel_ring_buffer *ring,
 		     struct i915_hw_context *to);
 
+static void do_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt)
+{
+	struct drm_device *dev = ppgtt->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_address_space *vm = &ppgtt->base;
+
+	if (ppgtt == dev_priv->mm.aliasing_ppgtt ||
+	    (list_empty(&vm->active_list) && list_empty(&vm->inactive_list))) {
+		ppgtt->base.cleanup(&ppgtt->base);
+		return;
+	}
+
+	/*
+	 * Make sure vmas are unbound before we take down the drm_mm
+	 *
+	 * FIXME: Proper refcounting should take care of this, this shouldn't be
+	 * needed at all.
+	 */
+	if (!list_empty(&vm->active_list)) {
+		struct i915_vma *vma;
+
+		list_for_each_entry(vma, &vm->active_list, mm_list)
+			if (WARN_ON(list_empty(&vma->vma_link) ||
+				    list_is_singular(&vma->vma_link)))
+				break;
+
+		i915_gem_evict_vm(&ppgtt->base, true);
+	} else {
+		i915_gem_retire_requests(dev);
+		i915_gem_evict_vm(&ppgtt->base, false);
+	}
+
+	ppgtt->base.cleanup(&ppgtt->base);
+}
+
+static void ppgtt_release(struct kref *kref)
+{
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(kref, struct i915_hw_ppgtt, ref);
+
+	do_ppgtt_cleanup(ppgtt);
+	kfree(ppgtt);
+}
+
 static size_t get_context_alignment(struct drm_device *dev)
 {
 	if (IS_GEN6(dev))
@@ -258,8 +302,7 @@
 		 * context.
 		 */
 		ret = i915_gem_obj_ggtt_pin(ctx->obj,
-					    get_context_alignment(dev),
-					    false, false);
+					    get_context_alignment(dev), 0);
 		if (ret) {
 			DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret);
 			goto err_destroy;
@@ -335,8 +378,7 @@
 
 		if (i == RCS) {
 			WARN_ON(i915_gem_obj_ggtt_pin(dctx->obj,
-						      get_context_alignment(dev),
-						      false, false));
+						      get_context_alignment(dev), 0));
 			/* Fake a finish/inactive */
 			dctx->obj->base.write_domain = 0;
 			dctx->obj->active = 0;
@@ -612,8 +654,7 @@
 	/* Trying to pin first makes error handling easier. */
 	if (ring == &dev_priv->ring[RCS]) {
 		ret = i915_gem_obj_ggtt_pin(to->obj,
-					    get_context_alignment(ring->dev),
-					    false, false);
+					    get_context_alignment(ring->dev), 0);
 		if (ret)
 			return ret;
 	}
@@ -717,7 +758,7 @@
  * i915_switch_context() - perform a GPU context switch.
  * @ring: ring for which we'll execute the context switch
  * @file_priv: file_priv associated with the context, may be NULL
- * @id: context id number
+ * @to: the context to switch to
  *
  * The context life cycle is simple. The context refcount is incremented and
  * decremented by 1 and create and destroy. If the context is in use by the GPU,
@@ -749,9 +790,6 @@
 	struct i915_hw_context *ctx;
 	int ret;
 
-	if (!(dev->driver->driver_features & DRIVER_GEM))
-		return -ENODEV;
-
 	if (!HAS_HW_CONTEXTS(dev))
 		return -ENODEV;
 
@@ -778,9 +816,6 @@
 	struct i915_hw_context *ctx;
 	int ret;
 
-	if (!(dev->driver->driver_features & DRIVER_GEM))
-		return -ENODEV;
-
 	if (args->ctx_id == DEFAULT_CONTEXT_ID)
 		return -ENOENT;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 5168d6a..8a78f78 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -68,7 +68,7 @@
 int
 i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
 			 int min_size, unsigned alignment, unsigned cache_level,
-			 bool mappable, bool nonblocking)
+			 unsigned flags)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct list_head eviction_list, unwind_list;
@@ -76,7 +76,7 @@
 	int ret = 0;
 	int pass = 0;
 
-	trace_i915_gem_evict(dev, min_size, alignment, mappable);
+	trace_i915_gem_evict(dev, min_size, alignment, flags);
 
 	/*
 	 * The goal is to evict objects and amalgamate space in LRU order.
@@ -102,7 +102,7 @@
 	 */
 
 	INIT_LIST_HEAD(&unwind_list);
-	if (mappable) {
+	if (flags & PIN_MAPPABLE) {
 		BUG_ON(!i915_is_ggtt(vm));
 		drm_mm_init_scan_with_range(&vm->mm, min_size,
 					    alignment, cache_level, 0,
@@ -117,7 +117,7 @@
 			goto found;
 	}
 
-	if (nonblocking)
+	if (flags & PIN_NONBLOCK)
 		goto none;
 
 	/* Now merge in the soon-to-be-expired objects... */
@@ -141,7 +141,7 @@
 	/* Can we unpin some objects such as idle hw contents,
 	 * or pending flips?
 	 */
-	if (nonblocking)
+	if (flags & PIN_NONBLOCK)
 		return -ENOSPC;
 
 	/* Only idle the GPU and repeat the search once */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 032def9..3851a1b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -544,19 +544,23 @@
 	struct drm_i915_gem_object *obj = vma->obj;
 	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
 	bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
-	bool need_fence, need_mappable;
-	u32 flags = (entry->flags & EXEC_OBJECT_NEEDS_GTT) &&
-		!vma->obj->has_global_gtt_mapping ? GLOBAL_BIND : 0;
+	bool need_fence;
+	unsigned flags;
 	int ret;
 
+	flags = 0;
+
 	need_fence =
 		has_fenced_gpu_access &&
 		entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
 		obj->tiling_mode != I915_TILING_NONE;
-	need_mappable = need_fence || need_reloc_mappable(vma);
+	if (need_fence || need_reloc_mappable(vma))
+		flags |= PIN_MAPPABLE;
 
-	ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, need_mappable,
-				  false);
+	if (entry->flags & EXEC_OBJECT_NEEDS_GTT)
+		flags |= PIN_GLOBAL;
+
+	ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags);
 	if (ret)
 		return ret;
 
@@ -585,8 +589,6 @@
 		obj->base.pending_write_domain = I915_GEM_DOMAIN_RENDER;
 	}
 
-	vma->bind_vma(vma, obj->cache_level, flags);
-
 	return 0;
 }
 
@@ -1180,6 +1182,24 @@
 	}
 	batch_obj->base.pending_read_domains |= I915_GEM_DOMAIN_COMMAND;
 
+	if (i915_needs_cmd_parser(ring)) {
+		ret = i915_parse_cmds(ring,
+				      batch_obj,
+				      args->batch_start_offset,
+				      file->is_master);
+		if (ret)
+			goto err;
+
+		/*
+		 * XXX: Actually do this when enabling batch copy...
+		 *
+		 * Set the DISPATCH_SECURE bit to remove the NON_SECURE bit
+		 * from MI_BATCH_BUFFER_START commands issued in the
+		 * dispatch_execbuffer implementations. We specifically don't
+		 * want that set when the command parser is enabled.
+		 */
+	}
+
 	/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
 	 * batch" bit. Hence we need to pin secure batches into the global gtt.
 	 * hsw should have this fixed, but bdw mucks it up again. */
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a4364ae..63a6dc7 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1,5 +1,6 @@
 /*
  * Copyright © 2010 Daniel Vetter
+ * Copyright © 2011-2014 Intel Corporation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -29,6 +30,29 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+bool intel_enable_ppgtt(struct drm_device *dev, bool full)
+{
+	if (i915.enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
+		return false;
+
+	if (i915.enable_ppgtt == 1 && full)
+		return false;
+
+#ifdef CONFIG_INTEL_IOMMU
+	/* Disable ppgtt on SNB if VT-d is on. */
+	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
+		DRM_INFO("Disabling PPGTT because VT-d is on\n");
+		return false;
+	}
+#endif
+
+	/* Full ppgtt disabled by default for now due to issues. */
+	if (full)
+		return false; /* HAS_PPGTT(dev) */
+	else
+		return HAS_ALIASING_PPGTT(dev);
+}
+
 #define GEN6_PPGTT_PD_ENTRIES 512
 #define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t))
 typedef uint64_t gen8_gtt_pte_t;
@@ -64,7 +88,19 @@
 
 #define GEN8_PTES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_gtt_pte_t))
 #define GEN8_PDES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
-#define GEN8_LEGACY_PDPS		4
+
+/* GEN8 legacy style addressis defined as a 3 level page table:
+ * 31:30 | 29:21 | 20:12 |  11:0
+ * PDPE  |  PDE  |  PTE  | offset
+ * The difference as compared to normal x86 3 level page table is the PDPEs are
+ * programmed via register.
+ */
+#define GEN8_PDPE_SHIFT			30
+#define GEN8_PDPE_MASK			0x3
+#define GEN8_PDE_SHIFT			21
+#define GEN8_PDE_MASK			0x1ff
+#define GEN8_PTE_SHIFT			12
+#define GEN8_PTE_MASK			0x1ff
 
 #define PPAT_UNCACHED_INDEX		(_PAGE_PWT | _PAGE_PCD)
 #define PPAT_CACHED_PDE_INDEX		0 /* WB LLC */
@@ -254,185 +290,337 @@
 }
 
 static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
-				   unsigned first_entry,
-				   unsigned num_entries,
+				   uint64_t start,
+				   uint64_t length,
 				   bool use_scratch)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen8_gtt_pte_t *pt_vaddr, scratch_pte;
-	unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE;
-	unsigned first_pte = first_entry % GEN8_PTES_PER_PAGE;
+	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
+	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
+	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	unsigned last_pte, i;
 
 	scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr,
 				      I915_CACHE_LLC, use_scratch);
 
 	while (num_entries) {
-		struct page *page_table = &ppgtt->gen8_pt_pages[act_pt];
+		struct page *page_table = ppgtt->gen8_pt_pages[pdpe][pde];
 
-		last_pte = first_pte + num_entries;
+		last_pte = pte + num_entries;
 		if (last_pte > GEN8_PTES_PER_PAGE)
 			last_pte = GEN8_PTES_PER_PAGE;
 
 		pt_vaddr = kmap_atomic(page_table);
 
-		for (i = first_pte; i < last_pte; i++)
+		for (i = pte; i < last_pte; i++) {
 			pt_vaddr[i] = scratch_pte;
+			num_entries--;
+		}
 
 		kunmap_atomic(pt_vaddr);
 
-		num_entries -= last_pte - first_pte;
-		first_pte = 0;
-		act_pt++;
+		pte = 0;
+		if (++pde == GEN8_PDES_PER_PAGE) {
+			pdpe++;
+			pde = 0;
+		}
 	}
 }
 
 static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
-				      unsigned first_entry,
+				      uint64_t start,
 				      enum i915_cache_level cache_level)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen8_gtt_pte_t *pt_vaddr;
-	unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE;
-	unsigned act_pte = first_entry % GEN8_PTES_PER_PAGE;
+	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
+	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
+	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
 	struct sg_page_iter sg_iter;
 
 	pt_vaddr = NULL;
-	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
-		if (pt_vaddr == NULL)
-			pt_vaddr = kmap_atomic(&ppgtt->gen8_pt_pages[act_pt]);
 
-		pt_vaddr[act_pte] =
+	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
+		if (WARN_ON(pdpe >= GEN8_LEGACY_PDPS))
+			break;
+
+		if (pt_vaddr == NULL)
+			pt_vaddr = kmap_atomic(ppgtt->gen8_pt_pages[pdpe][pde]);
+
+		pt_vaddr[pte] =
 			gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
 					cache_level, true);
-		if (++act_pte == GEN8_PTES_PER_PAGE) {
+		if (++pte == GEN8_PTES_PER_PAGE) {
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
-			act_pt++;
-			act_pte = 0;
+			if (++pde == GEN8_PDES_PER_PAGE) {
+				pdpe++;
+				pde = 0;
+			}
+			pte = 0;
 		}
 	}
 	if (pt_vaddr)
 		kunmap_atomic(pt_vaddr);
 }
 
+static void gen8_free_page_tables(struct page **pt_pages)
+{
+	int i;
+
+	if (pt_pages == NULL)
+		return;
+
+	for (i = 0; i < GEN8_PDES_PER_PAGE; i++)
+		if (pt_pages[i])
+			__free_pages(pt_pages[i], 0);
+}
+
+static void gen8_ppgtt_free(const struct i915_hw_ppgtt *ppgtt)
+{
+	int i;
+
+	for (i = 0; i < ppgtt->num_pd_pages; i++) {
+		gen8_free_page_tables(ppgtt->gen8_pt_pages[i]);
+		kfree(ppgtt->gen8_pt_pages[i]);
+		kfree(ppgtt->gen8_pt_dma_addr[i]);
+	}
+
+	__free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT));
+}
+
+static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
+{
+	struct pci_dev *hwdev = ppgtt->base.dev->pdev;
+	int i, j;
+
+	for (i = 0; i < ppgtt->num_pd_pages; i++) {
+		/* TODO: In the future we'll support sparse mappings, so this
+		 * will have to change. */
+		if (!ppgtt->pd_dma_addr[i])
+			continue;
+
+		pci_unmap_page(hwdev, ppgtt->pd_dma_addr[i], PAGE_SIZE,
+			       PCI_DMA_BIDIRECTIONAL);
+
+		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
+			dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j];
+			if (addr)
+				pci_unmap_page(hwdev, addr, PAGE_SIZE,
+					       PCI_DMA_BIDIRECTIONAL);
+		}
+	}
+}
+
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
-	int i, j;
 
 	list_del(&vm->global_link);
 	drm_mm_takedown(&vm->mm);
 
-	for (i = 0; i < ppgtt->num_pd_pages ; i++) {
-		if (ppgtt->pd_dma_addr[i]) {
-			pci_unmap_page(ppgtt->base.dev->pdev,
-				       ppgtt->pd_dma_addr[i],
-				       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-
-			for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
-				dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j];
-				if (addr)
-					pci_unmap_page(ppgtt->base.dev->pdev,
-						       addr,
-						       PAGE_SIZE,
-						       PCI_DMA_BIDIRECTIONAL);
-
-			}
-		}
-		kfree(ppgtt->gen8_pt_dma_addr[i]);
-	}
-
-	__free_pages(ppgtt->gen8_pt_pages, get_order(ppgtt->num_pt_pages << PAGE_SHIFT));
-	__free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT));
+	gen8_ppgtt_unmap_pages(ppgtt);
+	gen8_ppgtt_free(ppgtt);
 }
 
-/**
- * GEN8 legacy ppgtt programming is accomplished through 4 PDP registers with a
- * net effect resembling a 2-level page table in normal x86 terms. Each PDP
- * represents 1GB of memory
- * 4 * 512 * 512 * 4096 = 4GB legacy 32b address space.
- *
- * TODO: Do something with the size parameter
- **/
-static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
+static struct page **__gen8_alloc_page_tables(void)
 {
-	struct page *pt_pages;
-	int i, j, ret = -ENOMEM;
-	const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
-	const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
+	struct page **pt_pages;
+	int i;
 
-	if (size % (1<<30))
-		DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
+	pt_pages = kcalloc(GEN8_PDES_PER_PAGE, sizeof(struct page *), GFP_KERNEL);
+	if (!pt_pages)
+		return ERR_PTR(-ENOMEM);
 
-	/* FIXME: split allocation into smaller pieces. For now we only ever do
-	 * this once, but with full PPGTT, the multiple contiguous allocations
-	 * will be bad.
+	for (i = 0; i < GEN8_PDES_PER_PAGE; i++) {
+		pt_pages[i] = alloc_page(GFP_KERNEL);
+		if (!pt_pages[i])
+			goto bail;
+	}
+
+	return pt_pages;
+
+bail:
+	gen8_free_page_tables(pt_pages);
+	kfree(pt_pages);
+	return ERR_PTR(-ENOMEM);
+}
+
+static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt,
+					   const int max_pdp)
+{
+	struct page **pt_pages[GEN8_LEGACY_PDPS];
+	int i, ret;
+
+	for (i = 0; i < max_pdp; i++) {
+		pt_pages[i] = __gen8_alloc_page_tables();
+		if (IS_ERR(pt_pages[i])) {
+			ret = PTR_ERR(pt_pages[i]);
+			goto unwind_out;
+		}
+	}
+
+	/* NB: Avoid touching gen8_pt_pages until last to keep the allocation,
+	 * "atomic" - for cleanup purposes.
 	 */
+	for (i = 0; i < max_pdp; i++)
+		ppgtt->gen8_pt_pages[i] = pt_pages[i];
+
+	return 0;
+
+unwind_out:
+	while (i--) {
+		gen8_free_page_tables(pt_pages[i]);
+		kfree(pt_pages[i]);
+	}
+
+	return ret;
+}
+
+static int gen8_ppgtt_allocate_dma(struct i915_hw_ppgtt *ppgtt)
+{
+	int i;
+
+	for (i = 0; i < ppgtt->num_pd_pages; i++) {
+		ppgtt->gen8_pt_dma_addr[i] = kcalloc(GEN8_PDES_PER_PAGE,
+						     sizeof(dma_addr_t),
+						     GFP_KERNEL);
+		if (!ppgtt->gen8_pt_dma_addr[i])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int gen8_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt,
+						const int max_pdp)
+{
 	ppgtt->pd_pages = alloc_pages(GFP_KERNEL, get_order(max_pdp << PAGE_SHIFT));
 	if (!ppgtt->pd_pages)
 		return -ENOMEM;
 
-	pt_pages = alloc_pages(GFP_KERNEL, get_order(num_pt_pages << PAGE_SHIFT));
-	if (!pt_pages) {
-		__free_pages(ppgtt->pd_pages, get_order(max_pdp << PAGE_SHIFT));
-		return -ENOMEM;
-	}
-
-	ppgtt->gen8_pt_pages = pt_pages;
 	ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
-	ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT);
-	ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;
-	ppgtt->enable = gen8_ppgtt_enable;
-	ppgtt->switch_mm = gen8_mm_switch;
-	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
-	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
-	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
-	ppgtt->base.start = 0;
-	ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE;
-
 	BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
 
+	return 0;
+}
+
+static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
+			    const int max_pdp)
+{
+	int ret;
+
+	ret = gen8_ppgtt_allocate_page_directories(ppgtt, max_pdp);
+	if (ret)
+		return ret;
+
+	ret = gen8_ppgtt_allocate_page_tables(ppgtt, max_pdp);
+	if (ret) {
+		__free_pages(ppgtt->pd_pages, get_order(max_pdp << PAGE_SHIFT));
+		return ret;
+	}
+
+	ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;
+
+	ret = gen8_ppgtt_allocate_dma(ppgtt);
+	if (ret)
+		gen8_ppgtt_free(ppgtt);
+
+	return ret;
+}
+
+static int gen8_ppgtt_setup_page_directories(struct i915_hw_ppgtt *ppgtt,
+					     const int pd)
+{
+	dma_addr_t pd_addr;
+	int ret;
+
+	pd_addr = pci_map_page(ppgtt->base.dev->pdev,
+			       &ppgtt->pd_pages[pd], 0,
+			       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+
+	ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pd_addr);
+	if (ret)
+		return ret;
+
+	ppgtt->pd_dma_addr[pd] = pd_addr;
+
+	return 0;
+}
+
+static int gen8_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt,
+					const int pd,
+					const int pt)
+{
+	dma_addr_t pt_addr;
+	struct page *p;
+	int ret;
+
+	p = ppgtt->gen8_pt_pages[pd][pt];
+	pt_addr = pci_map_page(ppgtt->base.dev->pdev,
+			       p, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pt_addr);
+	if (ret)
+		return ret;
+
+	ppgtt->gen8_pt_dma_addr[pd][pt] = pt_addr;
+
+	return 0;
+}
+
+/**
+ * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
+ * with a net effect resembling a 2-level page table in normal x86 terms. Each
+ * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
+ * space.
+ *
+ * FIXME: split allocation into smaller pieces. For now we only ever do this
+ * once, but with full PPGTT, the multiple contiguous allocations will be bad.
+ * TODO: Do something with the size parameter
+ */
+static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
+{
+	const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
+	const int min_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
+	int i, j, ret;
+
+	if (size % (1<<30))
+		DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
+
+	/* 1. Do all our allocations for page directories and page tables. */
+	ret = gen8_ppgtt_alloc(ppgtt, max_pdp);
+	if (ret)
+		return ret;
+
 	/*
-	 * - Create a mapping for the page directories.
-	 * - For each page directory:
-	 *      allocate space for page table mappings.
-	 *      map each page table
+	 * 2. Create DMA mappings for the page directories and page tables.
 	 */
 	for (i = 0; i < max_pdp; i++) {
-		dma_addr_t temp;
-		temp = pci_map_page(ppgtt->base.dev->pdev,
-				    &ppgtt->pd_pages[i], 0,
-				    PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-		if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp))
-			goto err_out;
-
-		ppgtt->pd_dma_addr[i] = temp;
-
-		ppgtt->gen8_pt_dma_addr[i] = kmalloc(sizeof(dma_addr_t) * GEN8_PDES_PER_PAGE, GFP_KERNEL);
-		if (!ppgtt->gen8_pt_dma_addr[i])
-			goto err_out;
+		ret = gen8_ppgtt_setup_page_directories(ppgtt, i);
+		if (ret)
+			goto bail;
 
 		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
-			struct page *p = &pt_pages[i * GEN8_PDES_PER_PAGE + j];
-			temp = pci_map_page(ppgtt->base.dev->pdev,
-					    p, 0, PAGE_SIZE,
-					    PCI_DMA_BIDIRECTIONAL);
-
-			if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp))
-				goto err_out;
-
-			ppgtt->gen8_pt_dma_addr[i][j] = temp;
+			ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
+			if (ret)
+				goto bail;
 		}
 	}
 
-	/* For now, the PPGTT helper functions all require that the PDEs are
+	/*
+	 * 3. Map all the page directory entires to point to the page tables
+	 * we've allocated.
+	 *
+	 * For now, the PPGTT helper functions all require that the PDEs are
 	 * plugged in correctly. So we do that now/here. For aliasing PPGTT, we
-	 * will never need to touch the PDEs again */
+	 * will never need to touch the PDEs again.
+	 */
 	for (i = 0; i < max_pdp; i++) {
 		gen8_ppgtt_pde_t *pd_vaddr;
 		pd_vaddr = kmap_atomic(&ppgtt->pd_pages[i]);
@@ -444,20 +632,26 @@
 		kunmap_atomic(pd_vaddr);
 	}
 
-	ppgtt->base.clear_range(&ppgtt->base, 0,
-				ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE,
-				true);
+	ppgtt->enable = gen8_ppgtt_enable;
+	ppgtt->switch_mm = gen8_mm_switch;
+	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
+	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
+	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+	ppgtt->base.start = 0;
+	ppgtt->base.total = ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE;
+
+	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
 
 	DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n",
 			 ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp);
 	DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n",
-			 ppgtt->num_pt_pages,
-			 (ppgtt->num_pt_pages - num_pt_pages) +
-			 size % (1<<30));
+			 ppgtt->num_pd_entries,
+			 (ppgtt->num_pd_entries - min_pt_pages) + size % (1<<30));
 	return 0;
 
-err_out:
-	ppgtt->base.cleanup(&ppgtt->base);
+bail:
+	gen8_ppgtt_unmap_pages(ppgtt);
+	gen8_ppgtt_free(ppgtt);
 	return ret;
 }
 
@@ -759,13 +953,15 @@
 
 /* PPGTT support for Sandybdrige/Gen6 and later */
 static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
-				   unsigned first_entry,
-				   unsigned num_entries,
+				   uint64_t start,
+				   uint64_t length,
 				   bool use_scratch)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
@@ -792,12 +988,13 @@
 
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
-				      unsigned first_entry,
+				      uint64_t start,
 				      enum i915_cache_level cache_level)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen6_gtt_pte_t *pt_vaddr;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	struct sg_page_iter sg_iter;
@@ -821,38 +1018,49 @@
 		kunmap_atomic(pt_vaddr);
 }
 
-static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+static void gen6_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
 {
-	struct i915_hw_ppgtt *ppgtt =
-		container_of(vm, struct i915_hw_ppgtt, base);
 	int i;
 
-	list_del(&vm->global_link);
-	drm_mm_takedown(&ppgtt->base.mm);
-	drm_mm_remove_node(&ppgtt->node);
-
 	if (ppgtt->pt_dma_addr) {
 		for (i = 0; i < ppgtt->num_pd_entries; i++)
 			pci_unmap_page(ppgtt->base.dev->pdev,
 				       ppgtt->pt_dma_addr[i],
 				       4096, PCI_DMA_BIDIRECTIONAL);
 	}
+}
+
+static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+{
+	int i;
 
 	kfree(ppgtt->pt_dma_addr);
 	for (i = 0; i < ppgtt->num_pd_entries; i++)
 		__free_page(ppgtt->pt_pages[i]);
 	kfree(ppgtt->pt_pages);
-	kfree(ppgtt);
 }
 
-static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(vm, struct i915_hw_ppgtt, base);
+
+	list_del(&vm->global_link);
+	drm_mm_takedown(&ppgtt->base.mm);
+	drm_mm_remove_node(&ppgtt->node);
+
+	gen6_ppgtt_unmap_pages(ppgtt);
+	gen6_ppgtt_free(ppgtt);
+}
+
+static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 {
 #define GEN6_PD_ALIGN (PAGE_SIZE * 16)
 #define GEN6_PD_SIZE (GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE)
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool retried = false;
-	int i, ret;
+	int ret;
 
 	/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
 	 * allocator works in address space sizes, so it's multiplied by page
@@ -868,7 +1076,7 @@
 	if (ret == -ENOSPC && !retried) {
 		ret = i915_gem_evict_something(dev, &dev_priv->gtt.base,
 					       GEN6_PD_SIZE, GEN6_PD_ALIGN,
-					       I915_CACHE_NONE, false, true);
+					       I915_CACHE_NONE, 0);
 		if (ret)
 			return ret;
 
@@ -879,8 +1087,85 @@
 	if (ppgtt->node.start < dev_priv->gtt.mappable_end)
 		DRM_DEBUG("Forced to use aperture for PDEs\n");
 
-	ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
 	ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
+	return ret;
+}
+
+static int gen6_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
+{
+	int i;
+
+	ppgtt->pt_pages = kcalloc(ppgtt->num_pd_entries, sizeof(struct page *),
+				  GFP_KERNEL);
+
+	if (!ppgtt->pt_pages)
+		return -ENOMEM;
+
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL);
+		if (!ppgtt->pt_pages[i]) {
+			gen6_ppgtt_free(ppgtt);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
+{
+	int ret;
+
+	ret = gen6_ppgtt_allocate_page_directories(ppgtt);
+	if (ret)
+		return ret;
+
+	ret = gen6_ppgtt_allocate_page_tables(ppgtt);
+	if (ret) {
+		drm_mm_remove_node(&ppgtt->node);
+		return ret;
+	}
+
+	ppgtt->pt_dma_addr = kcalloc(ppgtt->num_pd_entries, sizeof(dma_addr_t),
+				     GFP_KERNEL);
+	if (!ppgtt->pt_dma_addr) {
+		drm_mm_remove_node(&ppgtt->node);
+		gen6_ppgtt_free(ppgtt);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int gen6_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt)
+{
+	struct drm_device *dev = ppgtt->base.dev;
+	int i;
+
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+
+		pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i], 0, 4096,
+				       PCI_DMA_BIDIRECTIONAL);
+
+		if (pci_dma_mapping_error(dev->pdev, pt_addr)) {
+			gen6_ppgtt_unmap_pages(ppgtt);
+			return -EIO;
+		}
+
+		ppgtt->pt_dma_addr[i] = pt_addr;
+	}
+
+	return 0;
+}
+
+static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+{
+	struct drm_device *dev = ppgtt->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
 	if (IS_GEN6(dev)) {
 		ppgtt->enable = gen6_ppgtt_enable;
 		ppgtt->switch_mm = gen6_mm_switch;
@@ -892,72 +1177,35 @@
 		ppgtt->switch_mm = gen7_mm_switch;
 	} else
 		BUG();
+
+	ret = gen6_ppgtt_alloc(ppgtt);
+	if (ret)
+		return ret;
+
+	ret = gen6_ppgtt_setup_page_tables(ppgtt);
+	if (ret) {
+		gen6_ppgtt_free(ppgtt);
+		return ret;
+	}
+
 	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
 	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
 	ppgtt->base.start = 0;
 	ppgtt->base.total = GEN6_PPGTT_PD_ENTRIES * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
-	ppgtt->pt_pages = kcalloc(ppgtt->num_pd_entries, sizeof(struct page *),
-				  GFP_KERNEL);
-	if (!ppgtt->pt_pages) {
-		drm_mm_remove_node(&ppgtt->node);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL);
-		if (!ppgtt->pt_pages[i])
-			goto err_pt_alloc;
-	}
-
-	ppgtt->pt_dma_addr = kcalloc(ppgtt->num_pd_entries, sizeof(dma_addr_t),
-				     GFP_KERNEL);
-	if (!ppgtt->pt_dma_addr)
-		goto err_pt_alloc;
-
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		dma_addr_t pt_addr;
-
-		pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i], 0, 4096,
-				       PCI_DMA_BIDIRECTIONAL);
-
-		if (pci_dma_mapping_error(dev->pdev, pt_addr)) {
-			ret = -EIO;
-			goto err_pd_pin;
-
-		}
-		ppgtt->pt_dma_addr[i] = pt_addr;
-	}
-
-	ppgtt->base.clear_range(&ppgtt->base, 0,
-				ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES, true);
 	ppgtt->debug_dump = gen6_dump_ppgtt;
 
+	ppgtt->pd_offset =
+		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_gtt_pte_t);
+
+	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
+
 	DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n",
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
-	ppgtt->pd_offset =
-		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_gtt_pte_t);
 
 	return 0;
-
-err_pd_pin:
-	if (ppgtt->pt_dma_addr) {
-		for (i--; i >= 0; i--)
-			pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i],
-				       4096, PCI_DMA_BIDIRECTIONAL);
-	}
-err_pt_alloc:
-	kfree(ppgtt->pt_dma_addr);
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		if (ppgtt->pt_pages[i])
-			__free_page(ppgtt->pt_pages[i]);
-	}
-	kfree(ppgtt->pt_pages);
-	drm_mm_remove_node(&ppgtt->node);
-
-	return ret;
 }
 
 int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
@@ -995,20 +1243,17 @@
 	       enum i915_cache_level cache_level,
 	       u32 flags)
 {
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
-
 	WARN_ON(flags);
 
-	vma->vm->insert_entries(vma->vm, vma->obj->pages, entry, cache_level);
+	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
+				cache_level);
 }
 
 static void ppgtt_unbind_vma(struct i915_vma *vma)
 {
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
-
 	vma->vm->clear_range(vma->vm,
-			     entry,
-			     vma->obj->base.size >> PAGE_SHIFT,
+			     vma->node.start,
+			     vma->obj->base.size,
 			     true);
 }
 
@@ -1092,8 +1337,8 @@
 	i915_check_and_clear_faults(dev);
 
 	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
-				       dev_priv->gtt.base.start / PAGE_SIZE,
-				       dev_priv->gtt.base.total / PAGE_SIZE,
+				       dev_priv->gtt.base.start,
+				       dev_priv->gtt.base.total,
 				       false);
 }
 
@@ -1107,8 +1352,8 @@
 
 	/* First fill our portion of the GTT with scratch pages */
 	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
-				       dev_priv->gtt.base.start / PAGE_SIZE,
-				       dev_priv->gtt.base.total / PAGE_SIZE,
+				       dev_priv->gtt.base.start,
+				       dev_priv->gtt.base.total,
 				       true);
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
@@ -1169,10 +1414,11 @@
 
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
-				     unsigned int first_entry,
+				     uint64_t start,
 				     enum i915_cache_level level)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	gen8_gtt_pte_t __iomem *gtt_entries =
 		(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
@@ -1214,10 +1460,11 @@
  */
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
-				     unsigned int first_entry,
+				     uint64_t start,
 				     enum i915_cache_level level)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	gen6_gtt_pte_t __iomem *gtt_entries =
 		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
@@ -1249,11 +1496,13 @@
 }
 
 static void gen8_ggtt_clear_range(struct i915_address_space *vm,
-				  unsigned int first_entry,
-				  unsigned int num_entries,
+				  uint64_t start,
+				  uint64_t length,
 				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	gen8_gtt_pte_t scratch_pte, __iomem *gtt_base =
 		(gen8_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
@@ -1273,11 +1522,13 @@
 }
 
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
-				  unsigned int first_entry,
-				  unsigned int num_entries,
+				  uint64_t start,
+				  uint64_t length,
 				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
 		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
@@ -1310,10 +1561,12 @@
 }
 
 static void i915_ggtt_clear_range(struct i915_address_space *vm,
-				  unsigned int first_entry,
-				  unsigned int num_entries,
+				  uint64_t start,
+				  uint64_t length,
 				  bool unused)
 {
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	intel_gtt_clear_range(first_entry, num_entries);
 }
 
@@ -1334,7 +1587,6 @@
 	struct drm_device *dev = vma->vm->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
 
 	/* If there is no aliasing PPGTT, or the caller needs a global mapping,
 	 * or we have a global mapping already but the cacheability flags have
@@ -1350,7 +1602,8 @@
 	if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
 		if (!obj->has_global_gtt_mapping ||
 		    (cache_level != obj->cache_level)) {
-			vma->vm->insert_entries(vma->vm, obj->pages, entry,
+			vma->vm->insert_entries(vma->vm, obj->pages,
+						vma->node.start,
 						cache_level);
 			obj->has_global_gtt_mapping = 1;
 		}
@@ -1361,7 +1614,9 @@
 	     (cache_level != obj->cache_level))) {
 		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
 		appgtt->base.insert_entries(&appgtt->base,
-					    vma->obj->pages, entry, cache_level);
+					    vma->obj->pages,
+					    vma->node.start,
+					    cache_level);
 		vma->obj->has_aliasing_ppgtt_mapping = 1;
 	}
 }
@@ -1371,11 +1626,11 @@
 	struct drm_device *dev = vma->vm->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
 
 	if (obj->has_global_gtt_mapping) {
-		vma->vm->clear_range(vma->vm, entry,
-				     vma->obj->base.size >> PAGE_SHIFT,
+		vma->vm->clear_range(vma->vm,
+				     vma->node.start,
+				     obj->base.size,
 				     true);
 		obj->has_global_gtt_mapping = 0;
 	}
@@ -1383,8 +1638,8 @@
 	if (obj->has_aliasing_ppgtt_mapping) {
 		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
 		appgtt->base.clear_range(&appgtt->base,
-					 entry,
-					 obj->base.size >> PAGE_SHIFT,
+					 vma->node.start,
+					 obj->base.size,
 					 true);
 		obj->has_aliasing_ppgtt_mapping = 0;
 	}
@@ -1469,14 +1724,14 @@
 
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt_vm->mm, hole_start, hole_end) {
-		const unsigned long count = (hole_end - hole_start) / PAGE_SIZE;
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
 			      hole_start, hole_end);
-		ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count, true);
+		ggtt_vm->clear_range(ggtt_vm, hole_start,
+				     hole_end - hole_start, true);
 	}
 
 	/* And finally clear the reserved guard page */
-	ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1, true);
+	ggtt_vm->clear_range(ggtt_vm, end - PAGE_SIZE, PAGE_SIZE, true);
 }
 
 void i915_gem_init_global_gtt(struct drm_device *dev)
@@ -1541,11 +1796,6 @@
 	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
 	if (bdw_gmch_ctl)
 		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
-	if (bdw_gmch_ctl > 4) {
-		WARN_ON(!i915.preliminary_hw_support);
-		return 4<<20;
-	}
-
 	return bdw_gmch_ctl << 20;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 1a24e84..d58b4e2 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -82,9 +82,22 @@
 	r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size,
 				    "Graphics Stolen Memory");
 	if (r == NULL) {
-		DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
-			  base, base + (uint32_t)dev_priv->gtt.stolen_size);
-		base = 0;
+		/*
+		 * One more attempt but this time requesting region from
+		 * base + 1, as we have seen that this resolves the region
+		 * conflict with the PCI Bus.
+		 * This is a BIOS w/a: Some BIOS wrap stolen in the root
+		 * PCI bus, but have an off-by-one error. Hence retry the
+		 * reservation starting from 1 instead of 0.
+		 */
+		r = devm_request_mem_region(dev->dev, base + 1,
+					    dev_priv->gtt.stolen_size - 1,
+					    "Graphics Stolen Memory");
+		if (r == NULL) {
+			DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
+				  base, base + (uint32_t)dev_priv->gtt.stolen_size);
+			base = 0;
+		}
 	}
 
 	return base;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 000b369..144a5e2 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -304,22 +304,54 @@
 	va_end(args);
 }
 
+static void print_error_obj(struct drm_i915_error_state_buf *m,
+			    struct drm_i915_error_object *obj)
+{
+	int page, offset, elt;
+
+	for (page = offset = 0; page < obj->page_count; page++) {
+		for (elt = 0; elt < PAGE_SIZE/4; elt++) {
+			err_printf(m, "%08x :  %08x\n", offset,
+				   obj->pages[page][elt]);
+			offset += 4;
+		}
+	}
+}
+
 int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			    const struct i915_error_state_file_priv *error_priv)
 {
 	struct drm_device *dev = error_priv->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error = error_priv->error;
-	int i, j, page, offset, elt;
+	int i, j, offset, elt;
+	int max_hangcheck_score;
 
 	if (!error) {
 		err_printf(m, "no error state collected\n");
 		goto out;
 	}
 
+	err_printf(m, "%s\n", error->error_msg);
 	err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
 		   error->time.tv_usec);
 	err_printf(m, "Kernel: " UTS_RELEASE "\n");
+	max_hangcheck_score = 0;
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+		if (error->ring[i].hangcheck_score > max_hangcheck_score)
+			max_hangcheck_score = error->ring[i].hangcheck_score;
+	}
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+		if (error->ring[i].hangcheck_score == max_hangcheck_score &&
+		    error->ring[i].pid != -1) {
+			err_printf(m, "Active process (on ring %s): %s [%d]\n",
+				   ring_str(i),
+				   error->ring[i].comm,
+				   error->ring[i].pid);
+		}
+	}
+	err_printf(m, "Reset count: %u\n", error->reset_count);
+	err_printf(m, "Suspend count: %u\n", error->suspend_count);
 	err_printf(m, "PCI ID: 0x%04x\n", dev->pdev->device);
 	err_printf(m, "EIR: 0x%08x\n", error->eir);
 	err_printf(m, "IER: 0x%08x\n", error->ier);
@@ -362,18 +394,23 @@
 	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
 		struct drm_i915_error_object *obj;
 
-		if ((obj = error->ring[i].batchbuffer)) {
-			err_printf(m, "%s --- gtt_offset = 0x%08x\n",
-				   dev_priv->ring[i].name,
+		obj = error->ring[i].batchbuffer;
+		if (obj) {
+			err_puts(m, dev_priv->ring[i].name);
+			if (error->ring[i].pid != -1)
+				err_printf(m, " (submitted by %s [%d])",
+					   error->ring[i].comm,
+					   error->ring[i].pid);
+			err_printf(m, " --- gtt_offset = 0x%08x\n",
 				   obj->gtt_offset);
-			offset = 0;
-			for (page = 0; page < obj->page_count; page++) {
-				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-					err_printf(m, "%08x :  %08x\n", offset,
-						   obj->pages[page][elt]);
-					offset += 4;
-				}
-			}
+			print_error_obj(m, obj);
+		}
+
+		obj = error->ring[i].wa_batchbuffer;
+		if (obj) {
+			err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
+				   dev_priv->ring[i].name, obj->gtt_offset);
+			print_error_obj(m, obj);
 		}
 
 		if (error->ring[i].num_requests) {
@@ -392,15 +429,7 @@
 			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
-			offset = 0;
-			for (page = 0; page < obj->page_count; page++) {
-				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-					err_printf(m, "%08x :  %08x\n",
-						   offset,
-						   obj->pages[page][elt]);
-					offset += 4;
-				}
-			}
+			print_error_obj(m, obj);
 		}
 
 		if ((obj = error->ring[i].hws_page)) {
@@ -666,7 +695,8 @@
  * It's only a small step better than a random number in its current form.
  */
 static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv,
-					 struct drm_i915_error_state *error)
+					 struct drm_i915_error_state *error,
+					 int *ring_id)
 {
 	uint32_t error_code = 0;
 	int i;
@@ -676,9 +706,14 @@
 	 * synchronization commands which almost always appear in the case
 	 * strictly a client bug. Use instdone to differentiate those some.
 	 */
-	for (i = 0; i < I915_NUM_RINGS; i++)
-		if (error->ring[i].hangcheck_action == HANGCHECK_HUNG)
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		if (error->ring[i].hangcheck_action == HANGCHECK_HUNG) {
+			if (ring_id)
+				*ring_id = i;
+
 			return error->ring[i].ipehr ^ error->ring[i].instdone;
+		}
+	}
 
 	return error_code;
 }
@@ -716,87 +751,6 @@
 	}
 }
 
-/* This assumes all batchbuffers are executed from the PPGTT. It might have to
- * change in the future. */
-static bool is_active_vm(struct i915_address_space *vm,
-			 struct intel_ring_buffer *ring)
-{
-	struct drm_device *dev = vm->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_hw_ppgtt *ppgtt;
-
-	if (INTEL_INFO(dev)->gen < 7)
-		return i915_is_ggtt(vm);
-
-	/* FIXME: This ignores that the global gtt vm is also on this list. */
-	ppgtt = container_of(vm, struct i915_hw_ppgtt, base);
-
-	if (INTEL_INFO(dev)->gen >= 8) {
-		u64 pdp0 = (u64)I915_READ(GEN8_RING_PDP_UDW(ring, 0)) << 32;
-		pdp0 |=  I915_READ(GEN8_RING_PDP_LDW(ring, 0));
-		return pdp0 == ppgtt->pd_dma_addr[0];
-	} else {
-		u32 pp_db;
-		pp_db = I915_READ(RING_PP_DIR_BASE(ring));
-		return (pp_db >> 10) == ppgtt->pd_offset;
-	}
-}
-
-static struct drm_i915_error_object *
-i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
-			     struct intel_ring_buffer *ring)
-{
-	struct i915_address_space *vm;
-	struct i915_vma *vma;
-	struct drm_i915_gem_object *obj;
-	bool found_active = false;
-	u32 seqno;
-
-	if (!ring->get_seqno)
-		return NULL;
-
-	if (HAS_BROKEN_CS_TLB(dev_priv->dev)) {
-		u32 acthd = I915_READ(ACTHD);
-
-		if (WARN_ON(ring->id != RCS))
-			return NULL;
-
-		obj = ring->scratch.obj;
-		if (obj != NULL &&
-		    acthd >= i915_gem_obj_ggtt_offset(obj) &&
-		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
-			return i915_error_ggtt_object_create(dev_priv, obj);
-	}
-
-	seqno = ring->get_seqno(ring, false);
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
-		if (!is_active_vm(vm, ring))
-			continue;
-
-		found_active = true;
-
-		list_for_each_entry(vma, &vm->active_list, mm_list) {
-			obj = vma->obj;
-			if (obj->ring != ring)
-				continue;
-
-			if (i915_seqno_passed(seqno, obj->last_read_seqno))
-				continue;
-
-			if ((obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) == 0)
-				continue;
-
-			/* We need to copy these to an anonymous buffer as the simplest
-			 * method to avoid being overwritten by userspace.
-			 */
-			return i915_error_object_create(dev_priv, obj, vm);
-		}
-	}
-
-	WARN_ON(!found_active);
-	return NULL;
-}
-
 static void i915_record_ring_state(struct drm_device *dev,
 				   struct intel_ring_buffer *ring,
 				   struct drm_i915_error_ring *ering)
@@ -945,8 +899,39 @@
 
 		i915_record_ring_state(dev, ring, &error->ring[i]);
 
-		error->ring[i].batchbuffer =
-			i915_error_first_batchbuffer(dev_priv, ring);
+		error->ring[i].pid = -1;
+		request = i915_gem_find_active_request(ring);
+		if (request) {
+			/* We need to copy these to an anonymous buffer
+			 * as the simplest method to avoid being overwritten
+			 * by userspace.
+			 */
+			error->ring[i].batchbuffer =
+				i915_error_object_create(dev_priv,
+							 request->batch_obj,
+							 request->ctx ?
+							 request->ctx->vm :
+							 &dev_priv->gtt.base);
+
+			if (HAS_BROKEN_CS_TLB(dev_priv->dev) &&
+			    ring->scratch.obj)
+				error->ring[i].wa_batchbuffer =
+					i915_error_ggtt_object_create(dev_priv,
+							     ring->scratch.obj);
+
+			if (request->file_priv) {
+				struct task_struct *task;
+
+				rcu_read_lock();
+				task = pid_task(request->file_priv->file->pid,
+						PIDTYPE_PID);
+				if (task) {
+					strcpy(error->ring[i].comm, task->comm);
+					error->ring[i].pid = task->pid;
+				}
+				rcu_read_unlock();
+			}
+		}
 
 		error->ring[i].ringbuffer =
 			i915_error_ggtt_object_create(dev_priv, ring->obj);
@@ -1113,6 +1098,40 @@
 	i915_get_extra_instdone(dev, error->extra_instdone);
 }
 
+static void i915_error_capture_msg(struct drm_device *dev,
+				   struct drm_i915_error_state *error,
+				   bool wedged,
+				   const char *error_msg)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 ecode;
+	int ring_id = -1, len;
+
+	ecode = i915_error_generate_code(dev_priv, error, &ring_id);
+
+	len = scnprintf(error->error_msg, sizeof(error->error_msg),
+			"GPU HANG: ecode %d:0x%08x", ring_id, ecode);
+
+	if (ring_id != -1 && error->ring[ring_id].pid != -1)
+		len += scnprintf(error->error_msg + len,
+				 sizeof(error->error_msg) - len,
+				 ", in %s [%d]",
+				 error->ring[ring_id].comm,
+				 error->ring[ring_id].pid);
+
+	scnprintf(error->error_msg + len, sizeof(error->error_msg) - len,
+		  ", reason: %s, action: %s",
+		  error_msg,
+		  wedged ? "reset" : "continue");
+}
+
+static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
+				   struct drm_i915_error_state *error)
+{
+	error->reset_count = i915_reset_count(&dev_priv->gpu_error);
+	error->suspend_count = dev_priv->suspend_count;
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -1122,19 +1141,13 @@
  * out a structure which becomes available in debugfs for user level tools
  * to pick up.
  */
-void i915_capture_error_state(struct drm_device *dev)
+void i915_capture_error_state(struct drm_device *dev, bool wedged,
+			      const char *error_msg)
 {
 	static bool warned;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error;
 	unsigned long flags;
-	uint32_t ecode;
-
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	error = dev_priv->gpu_error.first_error;
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
-	if (error)
-		return;
 
 	/* Account for pipe specific data like PIPE*STAT */
 	error = kzalloc(sizeof(*error), GFP_ATOMIC);
@@ -1143,30 +1156,22 @@
 		return;
 	}
 
-	DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n",
-		 dev->primary->index);
 	kref_init(&error->ref);
 
+	i915_capture_gen_state(dev_priv, error);
 	i915_capture_reg_state(dev_priv, error);
 	i915_gem_capture_buffers(dev_priv, error);
 	i915_gem_record_fences(dev, error);
 	i915_gem_record_rings(dev, error);
-	ecode = i915_error_generate_code(dev_priv, error);
-
-	if (!warned) {
-		DRM_INFO("GPU HANG [%x]\n", ecode);
-		DRM_INFO("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
-		DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
-		DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
-		DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n");
-		warned = true;
-	}
 
 	do_gettimeofday(&error->time);
 
 	error->overlay = intel_overlay_capture_error_state(dev);
 	error->display = intel_display_capture_error_state(dev);
 
+	i915_error_capture_msg(dev, error, wedged, error_msg);
+	DRM_INFO("%s\n", error->error_msg);
+
 	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
 	if (dev_priv->gpu_error.first_error == NULL) {
 		dev_priv->gpu_error.first_error = error;
@@ -1174,8 +1179,19 @@
 	}
 	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 
-	if (error)
+	if (error) {
 		i915_error_state_free(&error->ref);
+		return;
+	}
+
+	if (!warned) {
+		DRM_INFO("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
+		DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+		DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
+		DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n");
+		DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n", dev->primary->index);
+		warned = true;
+	}
 }
 
 void i915_error_state_get(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e9c94c9..be2713f 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -387,16 +387,15 @@
  *
  * Returns the previous state of underrun reporting.
  */
-bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
-					   enum pipe pipe, bool enable)
+bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
+					     enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	unsigned long flags;
 	bool ret;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	assert_spin_locked(&dev_priv->irq_lock);
 
 	ret = !intel_crtc->cpu_fifo_underrun_disabled;
 
@@ -415,10 +414,33 @@
 		broadwell_set_fifo_underrun_reporting(dev, pipe, enable);
 
 done:
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 	return ret;
 }
 
+bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
+					   enum pipe pipe, bool enable)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	ret = __intel_set_cpu_fifo_underrun_reporting(dev, pipe, enable);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	return ret;
+}
+
+static bool __cpu_fifo_underrun_reporting_enabled(struct drm_device *dev,
+						  enum pipe pipe)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+
+	return !intel_crtc->cpu_fifo_underrun_disabled;
+}
+
 /**
  * intel_set_pch_fifo_underrun_reporting - enable/disable FIFO underrun messages
  * @dev: drm device
@@ -472,39 +494,103 @@
 }
 
 
-void
-i915_enable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe, u32 mask)
+static void
+__i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
+		       u32 enable_mask, u32 status_mask)
 {
 	u32 reg = PIPESTAT(pipe);
-	u32 pipestat = I915_READ(reg) & 0x7fff0000;
+	u32 pipestat = I915_READ(reg) & PIPESTAT_INT_ENABLE_MASK;
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if ((pipestat & mask) == mask)
+	if (WARN_ON_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK ||
+	                 status_mask & ~PIPESTAT_INT_STATUS_MASK))
 		return;
 
+	if ((pipestat & enable_mask) == enable_mask)
+		return;
+
+	dev_priv->pipestat_irq_mask[pipe] |= status_mask;
+
 	/* Enable the interrupt, clear any pending status */
-	pipestat |= mask | (mask >> 16);
+	pipestat |= enable_mask | status_mask;
 	I915_WRITE(reg, pipestat);
 	POSTING_READ(reg);
 }
 
-void
-i915_disable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe, u32 mask)
+static void
+__i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
+		        u32 enable_mask, u32 status_mask)
 {
 	u32 reg = PIPESTAT(pipe);
-	u32 pipestat = I915_READ(reg) & 0x7fff0000;
+	u32 pipestat = I915_READ(reg) & PIPESTAT_INT_ENABLE_MASK;
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if ((pipestat & mask) == 0)
+	if (WARN_ON_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK ||
+	                 status_mask & ~PIPESTAT_INT_STATUS_MASK))
 		return;
 
-	pipestat &= ~mask;
+	if ((pipestat & enable_mask) == 0)
+		return;
+
+	dev_priv->pipestat_irq_mask[pipe] &= ~status_mask;
+
+	pipestat &= ~enable_mask;
 	I915_WRITE(reg, pipestat);
 	POSTING_READ(reg);
 }
 
+static u32 vlv_get_pipestat_enable_mask(struct drm_device *dev, u32 status_mask)
+{
+	u32 enable_mask = status_mask << 16;
+
+	/*
+	 * On pipe A we don't support the PSR interrupt yet, on pipe B the
+	 * same bit MBZ.
+	 */
+	if (WARN_ON_ONCE(status_mask & PIPE_A_PSR_STATUS_VLV))
+		return 0;
+
+	enable_mask &= ~(PIPE_FIFO_UNDERRUN_STATUS |
+			 SPRITE0_FLIP_DONE_INT_EN_VLV |
+			 SPRITE1_FLIP_DONE_INT_EN_VLV);
+	if (status_mask & SPRITE0_FLIP_DONE_INT_STATUS_VLV)
+		enable_mask |= SPRITE0_FLIP_DONE_INT_EN_VLV;
+	if (status_mask & SPRITE1_FLIP_DONE_INT_STATUS_VLV)
+		enable_mask |= SPRITE1_FLIP_DONE_INT_EN_VLV;
+
+	return enable_mask;
+}
+
+void
+i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
+		     u32 status_mask)
+{
+	u32 enable_mask;
+
+	if (IS_VALLEYVIEW(dev_priv->dev))
+		enable_mask = vlv_get_pipestat_enable_mask(dev_priv->dev,
+							   status_mask);
+	else
+		enable_mask = status_mask << 16;
+	__i915_enable_pipestat(dev_priv, pipe, enable_mask, status_mask);
+}
+
+void
+i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
+		      u32 status_mask)
+{
+	u32 enable_mask;
+
+	if (IS_VALLEYVIEW(dev_priv->dev))
+		enable_mask = vlv_get_pipestat_enable_mask(dev_priv->dev,
+							   status_mask);
+	else
+		enable_mask = status_mask << 16;
+	__i915_disable_pipestat(dev_priv, pipe, enable_mask, status_mask);
+}
+
 /**
  * i915_enable_asle_pipestat - enable ASLE pipestat for OpRegion
  */
@@ -518,10 +604,10 @@
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 
-	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_LEGACY_BLC_EVENT_ENABLE);
+	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_LEGACY_BLC_EVENT_STATUS);
 	if (INTEL_INFO(dev)->gen >= 4)
 		i915_enable_pipestat(dev_priv, PIPE_A,
-				     PIPE_LEGACY_BLC_EVENT_ENABLE);
+				     PIPE_LEGACY_BLC_EVENT_STATUS);
 
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
@@ -1222,8 +1308,8 @@
 	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
 		      GT_BSD_CS_ERROR_INTERRUPT |
 		      GT_RENDER_CS_MASTER_ERROR_INTERRUPT)) {
-		DRM_ERROR("GT error interrupt 0x%08x\n", gt_iir);
-		i915_handle_error(dev, false);
+		i915_handle_error(dev, false, "GT error interrupt 0x%08x",
+				  gt_iir);
 	}
 
 	if (gt_iir & GT_PARITY_ERROR(dev))
@@ -1470,8 +1556,9 @@
 			notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
 
 		if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) {
-			DRM_ERROR("VEBOX CS error interrupt 0x%08x\n", pm_iir);
-			i915_handle_error(dev_priv->dev, false);
+			i915_handle_error(dev_priv->dev, false,
+					  "VEBOX CS error interrupt 0x%08x",
+					  pm_iir);
 		}
 	}
 }
@@ -1479,18 +1566,48 @@
 static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 pipe_stats[I915_MAX_PIPES];
+	u32 pipe_stats[I915_MAX_PIPES] = { };
 	int pipe;
 
 	spin_lock(&dev_priv->irq_lock);
 	for_each_pipe(pipe) {
-		int reg = PIPESTAT(pipe);
-		pipe_stats[pipe] = I915_READ(reg);
+		int reg;
+		u32 mask, iir_bit = 0;
+
+		/*
+		 * PIPESTAT bits get signalled even when the interrupt is
+		 * disabled with the mask bits, and some of the status bits do
+		 * not generate interrupts at all (like the underrun bit). Hence
+		 * we need to be careful that we only handle what we want to
+		 * handle.
+		 */
+		mask = 0;
+		if (__cpu_fifo_underrun_reporting_enabled(dev, pipe))
+			mask |= PIPE_FIFO_UNDERRUN_STATUS;
+
+		switch (pipe) {
+		case PIPE_A:
+			iir_bit = I915_DISPLAY_PIPE_A_EVENT_INTERRUPT;
+			break;
+		case PIPE_B:
+			iir_bit = I915_DISPLAY_PIPE_B_EVENT_INTERRUPT;
+			break;
+		}
+		if (iir & iir_bit)
+			mask |= dev_priv->pipestat_irq_mask[pipe];
+
+		if (!mask)
+			continue;
+
+		reg = PIPESTAT(pipe);
+		mask |= PIPESTAT_INT_ENABLE_MASK;
+		pipe_stats[pipe] = I915_READ(reg) & mask;
 
 		/*
 		 * Clear the PIPE*STAT regs before the IIR
 		 */
-		if (pipe_stats[pipe] & 0x8000ffff)
+		if (pipe_stats[pipe] & (PIPE_FIFO_UNDERRUN_STATUS |
+					PIPESTAT_INT_STATUS_MASK))
 			I915_WRITE(reg, pipe_stats[pipe]);
 	}
 	spin_unlock(&dev_priv->irq_lock);
@@ -1761,7 +1878,7 @@
 static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum pipe i;
+	enum pipe pipe;
 
 	if (de_iir & DE_ERR_INT_IVB)
 		ivb_err_int_handler(dev);
@@ -1772,14 +1889,14 @@
 	if (de_iir & DE_GSE_IVB)
 		intel_opregion_asle_intr(dev);
 
-	for_each_pipe(i) {
-		if (de_iir & (DE_PIPE_VBLANK_IVB(i)))
-			drm_handle_vblank(dev, i);
+	for_each_pipe(pipe) {
+		if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)))
+			drm_handle_vblank(dev, pipe);
 
 		/* plane/pipes map 1:1 on ilk+ */
-		if (de_iir & DE_PLANE_FLIP_DONE_IVB(i)) {
-			intel_prepare_page_flip(dev, i);
-			intel_finish_page_flip_plane(dev, i);
+		if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) {
+			intel_prepare_page_flip(dev, pipe);
+			intel_finish_page_flip_plane(dev, pipe);
 		}
 	}
 
@@ -2173,11 +2290,18 @@
  * so userspace knows something bad happened (should trigger collection
  * of a ring dump etc.).
  */
-void i915_handle_error(struct drm_device *dev, bool wedged)
+void i915_handle_error(struct drm_device *dev, bool wedged,
+		       const char *fmt, ...)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	va_list args;
+	char error_msg[80];
 
-	i915_capture_error_state(dev);
+	va_start(args, fmt);
+	vscnprintf(error_msg, sizeof(error_msg), fmt, args);
+	va_end(args);
+
+	i915_capture_error_state(dev, wedged, error_msg);
 	i915_report_and_clear_eir(dev);
 
 	if (wedged) {
@@ -2269,13 +2393,13 @@
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	if (INTEL_INFO(dev)->gen >= 4)
 		i915_enable_pipestat(dev_priv, pipe,
-				     PIPE_START_VBLANK_INTERRUPT_ENABLE);
+				     PIPE_START_VBLANK_INTERRUPT_STATUS);
 	else
 		i915_enable_pipestat(dev_priv, pipe,
-				     PIPE_VBLANK_INTERRUPT_ENABLE);
+				     PIPE_VBLANK_INTERRUPT_STATUS);
 
 	/* maintain vblank delivery even in deep C-states */
-	if (dev_priv->info->gen == 3)
+	if (INTEL_INFO(dev)->gen == 3)
 		I915_WRITE(INSTPM, _MASKED_BIT_DISABLE(INSTPM_AGPBUSY_DIS));
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
@@ -2309,7 +2433,7 @@
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	i915_enable_pipestat(dev_priv, pipe,
-			     PIPE_START_VBLANK_INTERRUPT_ENABLE);
+			     PIPE_START_VBLANK_INTERRUPT_STATUS);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	return 0;
@@ -2340,12 +2464,12 @@
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	if (dev_priv->info->gen == 3)
+	if (INTEL_INFO(dev)->gen == 3)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_AGPBUSY_DIS));
 
 	i915_disable_pipestat(dev_priv, pipe,
-			      PIPE_VBLANK_INTERRUPT_ENABLE |
-			      PIPE_START_VBLANK_INTERRUPT_ENABLE);
+			      PIPE_VBLANK_INTERRUPT_STATUS |
+			      PIPE_START_VBLANK_INTERRUPT_STATUS);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
@@ -2368,7 +2492,7 @@
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	i915_disable_pipestat(dev_priv, pipe,
-			      PIPE_START_VBLANK_INTERRUPT_ENABLE);
+			      PIPE_START_VBLANK_INTERRUPT_STATUS);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
@@ -2480,9 +2604,9 @@
 	 */
 	tmp = I915_READ_CTL(ring);
 	if (tmp & RING_WAIT) {
-		DRM_ERROR("Kicking stuck wait on %s\n",
-			  ring->name);
-		i915_handle_error(dev, false);
+		i915_handle_error(dev, false,
+				  "Kicking stuck wait on %s",
+				  ring->name);
 		I915_WRITE_CTL(ring, tmp);
 		return HANGCHECK_KICK;
 	}
@@ -2492,9 +2616,9 @@
 		default:
 			return HANGCHECK_HUNG;
 		case 1:
-			DRM_ERROR("Kicking stuck semaphore on %s\n",
-				  ring->name);
-			i915_handle_error(dev, false);
+			i915_handle_error(dev, false,
+					  "Kicking stuck semaphore on %s",
+					  ring->name);
 			I915_WRITE_CTL(ring, tmp);
 			return HANGCHECK_KICK;
 		case 0:
@@ -2616,7 +2740,7 @@
 	}
 
 	if (rings_hung)
-		return i915_handle_error(dev, true);
+		return i915_handle_error(dev, true, "Ring hung");
 
 	if (busy_count)
 		/* Reset timer case chip hangs without another request
@@ -2912,44 +3036,113 @@
 	return 0;
 }
 
+static void valleyview_display_irqs_install(struct drm_i915_private *dev_priv)
+{
+	u32 pipestat_mask;
+	u32 iir_mask;
+
+	pipestat_mask = PIPESTAT_INT_STATUS_MASK |
+			PIPE_FIFO_UNDERRUN_STATUS;
+
+	I915_WRITE(PIPESTAT(PIPE_A), pipestat_mask);
+	I915_WRITE(PIPESTAT(PIPE_B), pipestat_mask);
+	POSTING_READ(PIPESTAT(PIPE_A));
+
+	pipestat_mask = PLANE_FLIP_DONE_INT_STATUS_VLV |
+			PIPE_CRC_DONE_INTERRUPT_STATUS;
+
+	i915_enable_pipestat(dev_priv, PIPE_A, pipestat_mask |
+					       PIPE_GMBUS_INTERRUPT_STATUS);
+	i915_enable_pipestat(dev_priv, PIPE_B, pipestat_mask);
+
+	iir_mask = I915_DISPLAY_PORT_INTERRUPT |
+		   I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
+		   I915_DISPLAY_PIPE_B_EVENT_INTERRUPT;
+	dev_priv->irq_mask &= ~iir_mask;
+
+	I915_WRITE(VLV_IIR, iir_mask);
+	I915_WRITE(VLV_IIR, iir_mask);
+	I915_WRITE(VLV_IMR, dev_priv->irq_mask);
+	I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
+	POSTING_READ(VLV_IER);
+}
+
+static void valleyview_display_irqs_uninstall(struct drm_i915_private *dev_priv)
+{
+	u32 pipestat_mask;
+	u32 iir_mask;
+
+	iir_mask = I915_DISPLAY_PORT_INTERRUPT |
+		   I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
+		   I915_DISPLAY_PIPE_A_EVENT_INTERRUPT;
+
+	dev_priv->irq_mask |= iir_mask;
+	I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
+	I915_WRITE(VLV_IMR, dev_priv->irq_mask);
+	I915_WRITE(VLV_IIR, iir_mask);
+	I915_WRITE(VLV_IIR, iir_mask);
+	POSTING_READ(VLV_IIR);
+
+	pipestat_mask = PLANE_FLIP_DONE_INT_STATUS_VLV |
+			PIPE_CRC_DONE_INTERRUPT_STATUS;
+
+	i915_disable_pipestat(dev_priv, PIPE_A, pipestat_mask |
+					        PIPE_GMBUS_INTERRUPT_STATUS);
+	i915_disable_pipestat(dev_priv, PIPE_B, pipestat_mask);
+
+	pipestat_mask = PIPESTAT_INT_STATUS_MASK |
+			PIPE_FIFO_UNDERRUN_STATUS;
+	I915_WRITE(PIPESTAT(PIPE_A), pipestat_mask);
+	I915_WRITE(PIPESTAT(PIPE_B), pipestat_mask);
+	POSTING_READ(PIPESTAT(PIPE_A));
+}
+
+void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv)
+{
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (dev_priv->display_irqs_enabled)
+		return;
+
+	dev_priv->display_irqs_enabled = true;
+
+	if (dev_priv->dev->irq_enabled)
+		valleyview_display_irqs_install(dev_priv);
+}
+
+void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv)
+{
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (!dev_priv->display_irqs_enabled)
+		return;
+
+	dev_priv->display_irqs_enabled = false;
+
+	if (dev_priv->dev->irq_enabled)
+		valleyview_display_irqs_uninstall(dev_priv);
+}
+
 static int valleyview_irq_postinstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	u32 enable_mask;
-	u32 pipestat_enable = PLANE_FLIP_DONE_INT_EN_VLV |
-		PIPE_CRC_DONE_ENABLE;
 	unsigned long irqflags;
 
-	enable_mask = I915_DISPLAY_PORT_INTERRUPT;
-	enable_mask |= I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT |
-		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-
-	/*
-	 *Leave vblank interrupts masked initially.  enable/disable will
-	 * toggle them based on usage.
-	 */
-	dev_priv->irq_mask = (~enable_mask) |
-		I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT |
-		I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
+	dev_priv->irq_mask = ~0;
 
 	I915_WRITE(PORT_HOTPLUG_EN, 0);
 	POSTING_READ(PORT_HOTPLUG_EN);
 
 	I915_WRITE(VLV_IMR, dev_priv->irq_mask);
-	I915_WRITE(VLV_IER, enable_mask);
+	I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
 	I915_WRITE(VLV_IIR, 0xffffffff);
-	I915_WRITE(PIPESTAT(0), 0xffff);
-	I915_WRITE(PIPESTAT(1), 0xffff);
 	POSTING_READ(VLV_IER);
 
 	/* Interrupt setup is already guaranteed to be single-threaded, this is
 	 * just to make the assert_spin_locked check happy. */
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	i915_enable_pipestat(dev_priv, PIPE_A, pipestat_enable);
-	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_EVENT_ENABLE);
-	i915_enable_pipestat(dev_priv, PIPE_B, pipestat_enable);
+	if (dev_priv->display_irqs_enabled)
+		valleyview_display_irqs_install(dev_priv);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	I915_WRITE(VLV_IIR, 0xffffffff);
@@ -3080,6 +3273,7 @@
 static void valleyview_irq_uninstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	unsigned long irqflags;
 	int pipe;
 
 	if (!dev_priv)
@@ -3093,8 +3287,14 @@
 	I915_WRITE(HWSTAM, 0xffffffff);
 	I915_WRITE(PORT_HOTPLUG_EN, 0);
 	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
-	for_each_pipe(pipe)
-		I915_WRITE(PIPESTAT(pipe), 0xffff);
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+	if (dev_priv->display_irqs_enabled)
+		valleyview_display_irqs_uninstall(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+
+	dev_priv->irq_mask = 0;
+
 	I915_WRITE(VLV_IIR, 0xffffffff);
 	I915_WRITE(VLV_IMR, 0xffffffff);
 	I915_WRITE(VLV_IER, 0x0);
@@ -3171,8 +3371,8 @@
 	/* Interrupt setup is already guaranteed to be single-threaded, this is
 	 * just to make the assert_spin_locked check happy. */
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_CRC_DONE_ENABLE);
-	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_CRC_DONE_ENABLE);
+	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_CRC_DONE_INTERRUPT_STATUS);
+	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_CRC_DONE_INTERRUPT_STATUS);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	return 0;
@@ -3233,7 +3433,9 @@
 		 */
 		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			i915_handle_error(dev, false);
+			i915_handle_error(dev, false,
+					  "Command parser error, iir 0x%08x",
+					  iir);
 
 		for_each_pipe(pipe) {
 			int reg = PIPESTAT(pipe);
@@ -3354,8 +3556,8 @@
 	/* Interrupt setup is already guaranteed to be single-threaded, this is
 	 * just to make the assert_spin_locked check happy. */
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_CRC_DONE_ENABLE);
-	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_CRC_DONE_ENABLE);
+	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_CRC_DONE_INTERRUPT_STATUS);
+	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_CRC_DONE_INTERRUPT_STATUS);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	return 0;
@@ -3415,7 +3617,9 @@
 		 */
 		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			i915_handle_error(dev, false);
+			i915_handle_error(dev, false,
+					  "Command parser error, iir 0x%08x",
+					  iir);
 
 		for_each_pipe(pipe) {
 			int reg = PIPESTAT(pipe);
@@ -3564,9 +3768,9 @@
 	/* Interrupt setup is already guaranteed to be single-threaded, this is
 	 * just to make the assert_spin_locked check happy. */
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_EVENT_ENABLE);
-	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_CRC_DONE_ENABLE);
-	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_CRC_DONE_ENABLE);
+	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_INTERRUPT_STATUS);
+	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_CRC_DONE_INTERRUPT_STATUS);
+	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_CRC_DONE_INTERRUPT_STATUS);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	/*
@@ -3652,7 +3856,9 @@
 		 */
 		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			i915_handle_error(dev, false);
+			i915_handle_error(dev, false,
+					  "Command parser error, iir 0x%08x",
+					  iir);
 
 		for_each_pipe(pipe) {
 			int reg = PIPESTAT(pipe);
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index c743057..a66ffb6 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -47,6 +47,8 @@
 	.prefault_disable = 0,
 	.reset = true,
 	.invert_brightness = 0,
+	.disable_display = 0,
+	.enable_cmd_parser = 0,
 };
 
 module_param_named(modeset, i915.modeset, int, 0400);
@@ -153,3 +155,10 @@
 	"report PCI device ID, subsystem vendor and subsystem device ID "
 	"to dri-devel@lists.freedesktop.org, if your machine needs it. "
 	"It will then be included in an upcoming module version.");
+
+module_param_named(disable_display, i915.disable_display, bool, 0600);
+MODULE_PARM_DESC(disable_display, "Disable display (default: false)");
+
+module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
+MODULE_PARM_DESC(enable_cmd_parser,
+		 "Enable command parsing (1=enabled, 0=disabled [default])");
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index cc3ea04..146609a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -175,6 +175,18 @@
 #define VGA_CR_DATA_CGA 0x3d5
 
 /*
+ * Instruction field definitions used by the command parser
+ */
+#define INSTR_CLIENT_SHIFT      29
+#define INSTR_CLIENT_MASK       0xE0000000
+#define   INSTR_MI_CLIENT       0x0
+#define   INSTR_BC_CLIENT       0x2
+#define   INSTR_RC_CLIENT       0x3
+#define INSTR_SUBCLIENT_SHIFT   27
+#define INSTR_SUBCLIENT_MASK    0x18000000
+#define   INSTR_MEDIA_SUBCLIENT 0x2
+
+/*
  * Memory interface instructions used by the kernel
  */
 #define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags))
@@ -377,14 +389,30 @@
 #define   DSPFREQSTAT_MASK			(0x3 << DSPFREQSTAT_SHIFT)
 #define   DSPFREQGUAR_SHIFT			14
 #define   DSPFREQGUAR_MASK			(0x3 << DSPFREQGUAR_SHIFT)
+
+/* See the PUNIT HAS v0.8 for the below bits */
+enum punit_power_well {
+	PUNIT_POWER_WELL_RENDER			= 0,
+	PUNIT_POWER_WELL_MEDIA			= 1,
+	PUNIT_POWER_WELL_DISP2D			= 3,
+	PUNIT_POWER_WELL_DPIO_CMN_BC		= 5,
+	PUNIT_POWER_WELL_DPIO_TX_B_LANES_01	= 6,
+	PUNIT_POWER_WELL_DPIO_TX_B_LANES_23	= 7,
+	PUNIT_POWER_WELL_DPIO_TX_C_LANES_01	= 8,
+	PUNIT_POWER_WELL_DPIO_TX_C_LANES_23	= 9,
+	PUNIT_POWER_WELL_DPIO_RX0		= 10,
+	PUNIT_POWER_WELL_DPIO_RX1		= 11,
+
+	PUNIT_POWER_WELL_NUM,
+};
+
 #define PUNIT_REG_PWRGT_CTRL			0x60
 #define PUNIT_REG_PWRGT_STATUS			0x61
-#define	  PUNIT_CLK_GATE			1
-#define	  PUNIT_PWR_RESET			2
-#define	  PUNIT_PWR_GATE			3
-#define	  RENDER_PWRGT				(PUNIT_PWR_GATE << 0)
-#define	  MEDIA_PWRGT				(PUNIT_PWR_GATE << 2)
-#define	  DISP2D_PWRGT				(PUNIT_PWR_GATE << 6)
+#define   PUNIT_PWRGT_MASK(power_well)		(3 << ((power_well) * 2))
+#define   PUNIT_PWRGT_PWR_ON(power_well)	(0 << ((power_well) * 2))
+#define   PUNIT_PWRGT_CLK_GATE(power_well)	(1 << ((power_well) * 2))
+#define   PUNIT_PWRGT_RESET(power_well)		(2 << ((power_well) * 2))
+#define   PUNIT_PWRGT_PWR_GATE(power_well)	(3 << ((power_well) * 2))
 
 #define PUNIT_REG_GPU_LFM			0xd3
 #define PUNIT_REG_GPU_FREQ_REQ			0xd4
@@ -789,7 +817,8 @@
 #define _3D_CHICKEN3	0x02090
 #define  _3D_CHICKEN_SF_DISABLE_OBJEND_CULL		(1 << 10)
 #define  _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL		(1 << 5)
-#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x)<<1)
+#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x)<<1) /* gen8+ */
+#define  _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH	(1 << 1) /* gen6 */
 
 #define MI_MODE		0x0209c
 # define VS_TIMER_DISPATCH				(1 << 6)
@@ -797,7 +826,12 @@
 # define ASYNC_FLIP_PERF_DISABLE			(1 << 14)
 
 #define GEN6_GT_MODE	0x20d0
-#define   GEN6_GT_MODE_HI				(1 << 9)
+#define GEN7_GT_MODE	0x7008
+#define   GEN6_WIZ_HASHING(hi, lo)			(((hi) << 9) | ((lo) << 7))
+#define   GEN6_WIZ_HASHING_8x8				GEN6_WIZ_HASHING(0, 0)
+#define   GEN6_WIZ_HASHING_8x4				GEN6_WIZ_HASHING(0, 1)
+#define   GEN6_WIZ_HASHING_16x4				GEN6_WIZ_HASHING(1, 0)
+#define   GEN6_WIZ_HASHING_MASK				(GEN6_WIZ_HASHING(1, 1) << 16)
 #define   GEN6_TD_FOUR_ROW_DISPATCH_DISABLE		(1 << 5)
 
 #define GFX_MODE	0x02520
@@ -943,6 +977,9 @@
 #define   GEN6_BLITTER_LOCK_SHIFT			16
 #define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
 
+#define GEN6_RC_SLEEP_PSMI_CONTROL	0x2050
+#define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
+
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	0x12050
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN6_BSD_SLEEP_FLUSH_DISABLE	(1 << 2)
@@ -1120,13 +1157,6 @@
 #define   FBC_REND_NUKE		(1<<2)
 #define   FBC_REND_CACHE_CLEAN	(1<<1)
 
-#define _HSW_PIPE_SLICE_CHICKEN_1_A	0x420B0
-#define _HSW_PIPE_SLICE_CHICKEN_1_B	0x420B4
-#define   HSW_BYPASS_FBC_QUEUE		(1<<22)
-#define HSW_PIPE_SLICE_CHICKEN_1(pipe) _PIPE(pipe, + \
-					     _HSW_PIPE_SLICE_CHICKEN_1_A, + \
-					     _HSW_PIPE_SLICE_CHICKEN_1_B)
-
 /*
  * GPIO regs
  */
@@ -1204,8 +1234,8 @@
  */
 #define DPLL_A_OFFSET 0x6014
 #define DPLL_B_OFFSET 0x6018
-#define DPLL(pipe) (dev_priv->info->dpll_offsets[pipe] + \
-		    dev_priv->info->display_mmio_offset)
+#define DPLL(pipe) (dev_priv->info.dpll_offsets[pipe] + \
+		    dev_priv->info.display_mmio_offset)
 
 #define VGA0	0x6000
 #define VGA1	0x6004
@@ -1282,8 +1312,8 @@
 
 #define DPLL_A_MD_OFFSET 0x601c /* 965+ only */
 #define DPLL_B_MD_OFFSET 0x6020 /* 965+ only */
-#define DPLL_MD(pipe) (dev_priv->info->dpll_md_offsets[pipe] + \
-		       dev_priv->info->display_mmio_offset)
+#define DPLL_MD(pipe) (dev_priv->info.dpll_md_offsets[pipe] + \
+		       dev_priv->info.display_mmio_offset)
 
 /*
  * UDI pixel divider, controlling how many pixels are stuffed into a packet.
@@ -1352,7 +1382,7 @@
 #define  DSTATE_PLL_D3_OFF			(1<<3)
 #define  DSTATE_GFX_CLOCK_GATING		(1<<1)
 #define  DSTATE_DOT_CLOCK_GATING		(1<<0)
-#define DSPCLK_GATE_D	(dev_priv->info->display_mmio_offset + 0x6200)
+#define DSPCLK_GATE_D	(dev_priv->info.display_mmio_offset + 0x6200)
 # define DPUNIT_B_CLOCK_GATE_DISABLE		(1 << 30) /* 965 */
 # define VSUNIT_CLOCK_GATE_DISABLE		(1 << 29) /* 965 */
 # define VRHUNIT_CLOCK_GATE_DISABLE		(1 << 28) /* 965 */
@@ -1478,8 +1508,8 @@
  */
 #define PALETTE_A_OFFSET 0xa000
 #define PALETTE_B_OFFSET 0xa800
-#define PALETTE(pipe) (dev_priv->info->palette_offsets[pipe] + \
-		       dev_priv->info->display_mmio_offset)
+#define PALETTE(pipe) (dev_priv->info.palette_offsets[pipe] + \
+		       dev_priv->info.display_mmio_offset)
 
 /* MCH MMIO space */
 
@@ -1969,9 +1999,9 @@
 #define TRANSCODER_C_OFFSET 0x62000
 #define TRANSCODER_EDP_OFFSET 0x6f000
 
-#define _TRANSCODER2(pipe, reg) (dev_priv->info->trans_offsets[(pipe)] - \
-	dev_priv->info->trans_offsets[TRANSCODER_A] + (reg) + \
-	dev_priv->info->display_mmio_offset)
+#define _TRANSCODER2(pipe, reg) (dev_priv->info.trans_offsets[(pipe)] - \
+	dev_priv->info.trans_offsets[TRANSCODER_A] + (reg) + \
+	dev_priv->info.display_mmio_offset)
 
 #define HTOTAL(trans) _TRANSCODER2(trans, _HTOTAL_A)
 #define HBLANK(trans) _TRANSCODER2(trans, _HBLANK_A)
@@ -2098,7 +2128,7 @@
 
 
 /* Hotplug control (945+ only) */
-#define PORT_HOTPLUG_EN		(dev_priv->info->display_mmio_offset + 0x61110)
+#define PORT_HOTPLUG_EN		(dev_priv->info.display_mmio_offset + 0x61110)
 #define   PORTB_HOTPLUG_INT_EN			(1 << 29)
 #define   PORTC_HOTPLUG_INT_EN			(1 << 28)
 #define   PORTD_HOTPLUG_INT_EN			(1 << 27)
@@ -2128,7 +2158,7 @@
 #define CRT_HOTPLUG_DETECT_VOLTAGE_325MV	(0 << 2)
 #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV	(1 << 2)
 
-#define PORT_HOTPLUG_STAT	(dev_priv->info->display_mmio_offset + 0x61114)
+#define PORT_HOTPLUG_STAT	(dev_priv->info.display_mmio_offset + 0x61114)
 /*
  * HDMI/DP bits are gen4+
  *
@@ -2346,9 +2376,7 @@
 #define VIDEO_DIP_CTL		0x61170
 /* Pre HSW: */
 #define   VIDEO_DIP_ENABLE		(1 << 31)
-#define   VIDEO_DIP_PORT_B		(1 << 29)
-#define   VIDEO_DIP_PORT_C		(2 << 29)
-#define   VIDEO_DIP_PORT_D		(3 << 29)
+#define   VIDEO_DIP_PORT(port)		((port) << 29)
 #define   VIDEO_DIP_PORT_MASK		(3 << 29)
 #define   VIDEO_DIP_ENABLE_GCP		(1 << 25)
 #define   VIDEO_DIP_ENABLE_AVI		(1 << 21)
@@ -2405,7 +2433,7 @@
 #define PP_DIVISOR	0x61210
 
 /* Panel fitting */
-#define PFIT_CONTROL	(dev_priv->info->display_mmio_offset + 0x61230)
+#define PFIT_CONTROL	(dev_priv->info.display_mmio_offset + 0x61230)
 #define   PFIT_ENABLE		(1 << 31)
 #define   PFIT_PIPE_MASK	(3 << 29)
 #define   PFIT_PIPE_SHIFT	29
@@ -2423,7 +2451,7 @@
 #define   PFIT_SCALING_PROGRAMMED (1 << 26)
 #define   PFIT_SCALING_PILLAR	(2 << 26)
 #define   PFIT_SCALING_LETTER	(3 << 26)
-#define PFIT_PGM_RATIOS	(dev_priv->info->display_mmio_offset + 0x61234)
+#define PFIT_PGM_RATIOS	(dev_priv->info.display_mmio_offset + 0x61234)
 /* Pre-965 */
 #define		PFIT_VERT_SCALE_SHIFT		20
 #define		PFIT_VERT_SCALE_MASK		0xfff00000
@@ -2435,25 +2463,25 @@
 #define		PFIT_HORIZ_SCALE_SHIFT_965	0
 #define		PFIT_HORIZ_SCALE_MASK_965	0x00001fff
 
-#define PFIT_AUTO_RATIOS (dev_priv->info->display_mmio_offset + 0x61238)
+#define PFIT_AUTO_RATIOS (dev_priv->info.display_mmio_offset + 0x61238)
 
-#define _VLV_BLC_PWM_CTL2_A (dev_priv->info->display_mmio_offset + 0x61250)
-#define _VLV_BLC_PWM_CTL2_B (dev_priv->info->display_mmio_offset + 0x61350)
+#define _VLV_BLC_PWM_CTL2_A (dev_priv->info.display_mmio_offset + 0x61250)
+#define _VLV_BLC_PWM_CTL2_B (dev_priv->info.display_mmio_offset + 0x61350)
 #define VLV_BLC_PWM_CTL2(pipe) _PIPE(pipe, _VLV_BLC_PWM_CTL2_A, \
 				     _VLV_BLC_PWM_CTL2_B)
 
-#define _VLV_BLC_PWM_CTL_A (dev_priv->info->display_mmio_offset + 0x61254)
-#define _VLV_BLC_PWM_CTL_B (dev_priv->info->display_mmio_offset + 0x61354)
+#define _VLV_BLC_PWM_CTL_A (dev_priv->info.display_mmio_offset + 0x61254)
+#define _VLV_BLC_PWM_CTL_B (dev_priv->info.display_mmio_offset + 0x61354)
 #define VLV_BLC_PWM_CTL(pipe) _PIPE(pipe, _VLV_BLC_PWM_CTL_A, \
 				    _VLV_BLC_PWM_CTL_B)
 
-#define _VLV_BLC_HIST_CTL_A (dev_priv->info->display_mmio_offset + 0x61260)
-#define _VLV_BLC_HIST_CTL_B (dev_priv->info->display_mmio_offset + 0x61360)
+#define _VLV_BLC_HIST_CTL_A (dev_priv->info.display_mmio_offset + 0x61260)
+#define _VLV_BLC_HIST_CTL_B (dev_priv->info.display_mmio_offset + 0x61360)
 #define VLV_BLC_HIST_CTL(pipe) _PIPE(pipe, _VLV_BLC_HIST_CTL_A, \
 				     _VLV_BLC_HIST_CTL_B)
 
 /* Backlight control */
-#define BLC_PWM_CTL2	(dev_priv->info->display_mmio_offset + 0x61250) /* 965+ only */
+#define BLC_PWM_CTL2	(dev_priv->info.display_mmio_offset + 0x61250) /* 965+ only */
 #define   BLM_PWM_ENABLE		(1 << 31)
 #define   BLM_COMBINATION_MODE		(1 << 30) /* gen4 only */
 #define   BLM_PIPE_SELECT		(1 << 29)
@@ -2476,7 +2504,7 @@
 #define   BLM_PHASE_IN_COUNT_MASK	(0xff << 8)
 #define   BLM_PHASE_IN_INCR_SHIFT	(0)
 #define   BLM_PHASE_IN_INCR_MASK	(0xff << 0)
-#define BLC_PWM_CTL	(dev_priv->info->display_mmio_offset + 0x61254)
+#define BLC_PWM_CTL	(dev_priv->info.display_mmio_offset + 0x61254)
 /*
  * This is the most significant 15 bits of the number of backlight cycles in a
  * complete cycle of the modulated backlight control.
@@ -2498,7 +2526,7 @@
 #define   BACKLIGHT_DUTY_CYCLE_MASK_PNV		(0xfffe)
 #define   BLM_POLARITY_PNV			(1 << 0) /* pnv only */
 
-#define BLC_HIST_CTL	(dev_priv->info->display_mmio_offset + 0x61260)
+#define BLC_HIST_CTL	(dev_priv->info.display_mmio_offset + 0x61260)
 
 /* New registers for PCH-split platforms. Safe where new bits show up, the
  * register layout machtes with gen4 BLC_PWM_CTL[12]. */
@@ -3253,6 +3281,7 @@
 #define   PIPE_LEGACY_BLC_EVENT_ENABLE		(1UL<<22)
 #define   PIPE_ODD_FIELD_INTERRUPT_ENABLE	(1UL<<21)
 #define   PIPE_EVEN_FIELD_INTERRUPT_ENABLE	(1UL<<20)
+#define   PIPE_B_PSR_INTERRUPT_ENABLE_VLV	(1UL<<19)
 #define   PIPE_HOTPLUG_TV_INTERRUPT_ENABLE	(1UL<<18) /* pre-965 */
 #define   PIPE_START_VBLANK_INTERRUPT_ENABLE	(1UL<<18) /* 965 or later */
 #define   PIPE_VBLANK_INTERRUPT_ENABLE		(1UL<<17)
@@ -3269,13 +3298,18 @@
 #define   PIPE_DISPLAY_LINE_COMPARE_STATUS	(1UL<<8)
 #define   PIPE_DPST_EVENT_STATUS		(1UL<<7)
 #define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
+#define   PIPE_A_PSR_STATUS_VLV			(1UL<<6)
 #define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL<<5)
 #define   PIPE_EVEN_FIELD_INTERRUPT_STATUS	(1UL<<4)
+#define   PIPE_B_PSR_STATUS_VLV			(1UL<<3)
 #define   PIPE_HOTPLUG_TV_INTERRUPT_STATUS	(1UL<<2) /* pre-965 */
 #define   PIPE_START_VBLANK_INTERRUPT_STATUS	(1UL<<2) /* 965 or later */
 #define   PIPE_VBLANK_INTERRUPT_STATUS		(1UL<<1)
 #define   PIPE_OVERLAY_UPDATED_STATUS		(1UL<<0)
 
+#define PIPESTAT_INT_ENABLE_MASK		0x7fff0000
+#define PIPESTAT_INT_STATUS_MASK		0x0000ffff
+
 #define PIPE_A_OFFSET	0x70000
 #define PIPE_B_OFFSET	0x71000
 #define PIPE_C_OFFSET	0x72000
@@ -3287,9 +3321,9 @@
  */
 #define PIPE_EDP_OFFSET	0x7f000
 
-#define _PIPE2(pipe, reg) (dev_priv->info->pipe_offsets[pipe] - \
-	dev_priv->info->pipe_offsets[PIPE_A] + (reg) + \
-	dev_priv->info->display_mmio_offset)
+#define _PIPE2(pipe, reg) (dev_priv->info.pipe_offsets[pipe] - \
+	dev_priv->info.pipe_offsets[PIPE_A] + (reg) + \
+	dev_priv->info.display_mmio_offset)
 
 #define PIPECONF(pipe) _PIPE2(pipe, _PIPEACONF)
 #define PIPEDSL(pipe)  _PIPE2(pipe, _PIPEADSL)
@@ -3351,7 +3385,7 @@
 #define   DSPARB_BEND_SHIFT	9 /* on 855 */
 #define   DSPARB_AEND_SHIFT	0
 
-#define DSPFW1			(dev_priv->info->display_mmio_offset + 0x70034)
+#define DSPFW1			(dev_priv->info.display_mmio_offset + 0x70034)
 #define   DSPFW_SR_SHIFT	23
 #define   DSPFW_SR_MASK		(0x1ff<<23)
 #define   DSPFW_CURSORB_SHIFT	16
@@ -3359,11 +3393,11 @@
 #define   DSPFW_PLANEB_SHIFT	8
 #define   DSPFW_PLANEB_MASK	(0x7f<<8)
 #define   DSPFW_PLANEA_MASK	(0x7f)
-#define DSPFW2			(dev_priv->info->display_mmio_offset + 0x70038)
+#define DSPFW2			(dev_priv->info.display_mmio_offset + 0x70038)
 #define   DSPFW_CURSORA_MASK	0x00003f00
 #define   DSPFW_CURSORA_SHIFT	8
 #define   DSPFW_PLANEC_MASK	(0x7f)
-#define DSPFW3			(dev_priv->info->display_mmio_offset + 0x7003c)
+#define DSPFW3			(dev_priv->info.display_mmio_offset + 0x7003c)
 #define   DSPFW_HPLL_SR_EN	(1<<31)
 #define   DSPFW_CURSOR_SR_SHIFT	24
 #define   PINEVIEW_SELF_REFRESH_EN	(1<<30)
@@ -3371,8 +3405,8 @@
 #define   DSPFW_HPLL_CURSOR_SHIFT	16
 #define   DSPFW_HPLL_CURSOR_MASK	(0x3f<<16)
 #define   DSPFW_HPLL_SR_MASK		(0x1ff)
-#define DSPFW4			(dev_priv->info->display_mmio_offset + 0x70070)
-#define DSPFW7			(dev_priv->info->display_mmio_offset + 0x7007c)
+#define DSPFW4			(dev_priv->info.display_mmio_offset + 0x70070)
+#define DSPFW7			(dev_priv->info.display_mmio_offset + 0x7007c)
 
 /* drain latency register values*/
 #define DRAIN_LATENCY_PRECISION_32	32
@@ -3496,12 +3530,12 @@
 #define   PIPE_PIXEL_MASK         0x00ffffff
 #define   PIPE_PIXEL_SHIFT        0
 /* GM45+ just has to be different */
-#define _PIPEA_FRMCOUNT_GM45	(dev_priv->info->display_mmio_offset + 0x70040)
-#define _PIPEA_FLIPCOUNT_GM45	(dev_priv->info->display_mmio_offset + 0x70044)
+#define _PIPEA_FRMCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x70040)
+#define _PIPEA_FLIPCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x70044)
 #define PIPE_FRMCOUNT_GM45(pipe) _PIPE(pipe, _PIPEA_FRMCOUNT_GM45, _PIPEB_FRMCOUNT_GM45)
 
 /* Cursor A & B regs */
-#define _CURACNTR		(dev_priv->info->display_mmio_offset + 0x70080)
+#define _CURACNTR		(dev_priv->info.display_mmio_offset + 0x70080)
 /* Old style CUR*CNTR flags (desktop 8xx) */
 #define   CURSOR_ENABLE		0x80000000
 #define   CURSOR_GAMMA_ENABLE	0x40000000
@@ -3524,16 +3558,16 @@
 #define   MCURSOR_PIPE_B	(1 << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
 #define   CURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
-#define _CURABASE		(dev_priv->info->display_mmio_offset + 0x70084)
-#define _CURAPOS		(dev_priv->info->display_mmio_offset + 0x70088)
+#define _CURABASE		(dev_priv->info.display_mmio_offset + 0x70084)
+#define _CURAPOS		(dev_priv->info.display_mmio_offset + 0x70088)
 #define   CURSOR_POS_MASK       0x007FF
 #define   CURSOR_POS_SIGN       0x8000
 #define   CURSOR_X_SHIFT        0
 #define   CURSOR_Y_SHIFT        16
 #define CURSIZE			0x700a0
-#define _CURBCNTR		(dev_priv->info->display_mmio_offset + 0x700c0)
-#define _CURBBASE		(dev_priv->info->display_mmio_offset + 0x700c4)
-#define _CURBPOS		(dev_priv->info->display_mmio_offset + 0x700c8)
+#define _CURBCNTR		(dev_priv->info.display_mmio_offset + 0x700c0)
+#define _CURBBASE		(dev_priv->info.display_mmio_offset + 0x700c4)
+#define _CURBPOS		(dev_priv->info.display_mmio_offset + 0x700c8)
 
 #define _CURBCNTR_IVB		0x71080
 #define _CURBBASE_IVB		0x71084
@@ -3608,44 +3642,44 @@
 #define I915_HI_DISPBASE(val)	(val & DISP_BASEADDR_MASK)
 
 /* VBIOS flags */
-#define SWF00			(dev_priv->info->display_mmio_offset + 0x71410)
-#define SWF01			(dev_priv->info->display_mmio_offset + 0x71414)
-#define SWF02			(dev_priv->info->display_mmio_offset + 0x71418)
-#define SWF03			(dev_priv->info->display_mmio_offset + 0x7141c)
-#define SWF04			(dev_priv->info->display_mmio_offset + 0x71420)
-#define SWF05			(dev_priv->info->display_mmio_offset + 0x71424)
-#define SWF06			(dev_priv->info->display_mmio_offset + 0x71428)
-#define SWF10			(dev_priv->info->display_mmio_offset + 0x70410)
-#define SWF11			(dev_priv->info->display_mmio_offset + 0x70414)
-#define SWF14			(dev_priv->info->display_mmio_offset + 0x71420)
-#define SWF30			(dev_priv->info->display_mmio_offset + 0x72414)
-#define SWF31			(dev_priv->info->display_mmio_offset + 0x72418)
-#define SWF32			(dev_priv->info->display_mmio_offset + 0x7241c)
+#define SWF00			(dev_priv->info.display_mmio_offset + 0x71410)
+#define SWF01			(dev_priv->info.display_mmio_offset + 0x71414)
+#define SWF02			(dev_priv->info.display_mmio_offset + 0x71418)
+#define SWF03			(dev_priv->info.display_mmio_offset + 0x7141c)
+#define SWF04			(dev_priv->info.display_mmio_offset + 0x71420)
+#define SWF05			(dev_priv->info.display_mmio_offset + 0x71424)
+#define SWF06			(dev_priv->info.display_mmio_offset + 0x71428)
+#define SWF10			(dev_priv->info.display_mmio_offset + 0x70410)
+#define SWF11			(dev_priv->info.display_mmio_offset + 0x70414)
+#define SWF14			(dev_priv->info.display_mmio_offset + 0x71420)
+#define SWF30			(dev_priv->info.display_mmio_offset + 0x72414)
+#define SWF31			(dev_priv->info.display_mmio_offset + 0x72418)
+#define SWF32			(dev_priv->info.display_mmio_offset + 0x7241c)
 
 /* Pipe B */
-#define _PIPEBDSL		(dev_priv->info->display_mmio_offset + 0x71000)
-#define _PIPEBCONF		(dev_priv->info->display_mmio_offset + 0x71008)
-#define _PIPEBSTAT		(dev_priv->info->display_mmio_offset + 0x71024)
+#define _PIPEBDSL		(dev_priv->info.display_mmio_offset + 0x71000)
+#define _PIPEBCONF		(dev_priv->info.display_mmio_offset + 0x71008)
+#define _PIPEBSTAT		(dev_priv->info.display_mmio_offset + 0x71024)
 #define _PIPEBFRAMEHIGH		0x71040
 #define _PIPEBFRAMEPIXEL	0x71044
-#define _PIPEB_FRMCOUNT_GM45	(dev_priv->info->display_mmio_offset + 0x71040)
-#define _PIPEB_FLIPCOUNT_GM45	(dev_priv->info->display_mmio_offset + 0x71044)
+#define _PIPEB_FRMCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x71040)
+#define _PIPEB_FLIPCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x71044)
 
 
 /* Display B control */
-#define _DSPBCNTR		(dev_priv->info->display_mmio_offset + 0x71180)
+#define _DSPBCNTR		(dev_priv->info.display_mmio_offset + 0x71180)
 #define   DISPPLANE_ALPHA_TRANS_ENABLE		(1<<15)
 #define   DISPPLANE_ALPHA_TRANS_DISABLE		0
 #define   DISPPLANE_SPRITE_ABOVE_DISPLAY	0
 #define   DISPPLANE_SPRITE_ABOVE_OVERLAY	(1)
-#define _DSPBADDR		(dev_priv->info->display_mmio_offset + 0x71184)
-#define _DSPBSTRIDE		(dev_priv->info->display_mmio_offset + 0x71188)
-#define _DSPBPOS		(dev_priv->info->display_mmio_offset + 0x7118C)
-#define _DSPBSIZE		(dev_priv->info->display_mmio_offset + 0x71190)
-#define _DSPBSURF		(dev_priv->info->display_mmio_offset + 0x7119C)
-#define _DSPBTILEOFF		(dev_priv->info->display_mmio_offset + 0x711A4)
-#define _DSPBOFFSET		(dev_priv->info->display_mmio_offset + 0x711A4)
-#define _DSPBSURFLIVE		(dev_priv->info->display_mmio_offset + 0x711AC)
+#define _DSPBADDR		(dev_priv->info.display_mmio_offset + 0x71184)
+#define _DSPBSTRIDE		(dev_priv->info.display_mmio_offset + 0x71188)
+#define _DSPBPOS		(dev_priv->info.display_mmio_offset + 0x7118C)
+#define _DSPBSIZE		(dev_priv->info.display_mmio_offset + 0x71190)
+#define _DSPBSURF		(dev_priv->info.display_mmio_offset + 0x7119C)
+#define _DSPBTILEOFF		(dev_priv->info.display_mmio_offset + 0x711A4)
+#define _DSPBOFFSET		(dev_priv->info.display_mmio_offset + 0x711A4)
+#define _DSPBSURFLIVE		(dev_priv->info.display_mmio_offset + 0x711AC)
 
 /* Sprite A control */
 #define _DVSACNTR		0x72180
@@ -4109,13 +4143,14 @@
 #define  ILK_ELPIN_409_SELECT	(1 << 25)
 #define  ILK_DPARB_GATE	(1<<22)
 #define  ILK_VSDPFD_FULL	(1<<21)
-#define ILK_DISPLAY_CHICKEN_FUSES	0x42014
-#define  ILK_INTERNAL_GRAPHICS_DISABLE	(1<<31)
-#define  ILK_INTERNAL_DISPLAY_DISABLE	(1<<30)
-#define  ILK_DISPLAY_DEBUG_DISABLE	(1<<29)
-#define  ILK_HDCP_DISABLE		(1<<25)
-#define  ILK_eDP_A_DISABLE		(1<<24)
-#define  ILK_DESKTOP			(1<<23)
+#define FUSE_STRAP			0x42014
+#define  ILK_INTERNAL_GRAPHICS_DISABLE	(1 << 31)
+#define  ILK_INTERNAL_DISPLAY_DISABLE	(1 << 30)
+#define  ILK_DISPLAY_DEBUG_DISABLE	(1 << 29)
+#define  ILK_HDCP_DISABLE		(1 << 25)
+#define  ILK_eDP_A_DISABLE		(1 << 24)
+#define  HSW_CDCLK_LIMIT		(1 << 24)
+#define  ILK_DESKTOP			(1 << 23)
 
 #define ILK_DSPCLK_GATE_D			0x42020
 #define   ILK_VRHUNIT_CLOCK_GATE_DISABLE	(1 << 28)
@@ -4134,7 +4169,8 @@
 
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
-#define  DPRS_MASK_VBLANK_SRD	(1 << 0)
+#define  HSW_FBCQ_DIS			(1 << 22)
+#define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
 #define CHICKEN_PIPESL_1(pipe) _PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
 
 #define DISP_ARB_CTL	0x45000
@@ -4158,7 +4194,7 @@
 #define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
 
 #define GEN7_L3CNTLREG1				0xB01C
-#define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C4FFF8C
+#define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
 #define  GEN7_L3AGDIS				(1<<19)
 
 #define GEN7_L3_CHICKEN_MODE_REGISTER		0xB030
@@ -4178,9 +4214,6 @@
 #define HSW_SCRATCH1				0xb038
 #define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
 
-#define HSW_FUSE_STRAP		0x42014
-#define  HSW_CDCLK_LIMIT	(1 << 24)
-
 /* PCH */
 
 /* south display engine interrupt: IBX */
@@ -4895,6 +4928,9 @@
 #define GEN7_UCGCTL4				0x940c
 #define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)
 
+#define GEN8_UCGCTL6				0x9430
+#define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
+
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
 #define   GEN6_FREQUENCY(x)			((x)<<25)
@@ -5040,6 +5076,10 @@
 #define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1<<10)
 #define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1<<3)
 
+#define GEN8_ROW_CHICKEN		0xe4f0
+#define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1<<8)
+#define   STALL_DOP_GATING_DISABLE		(1<<5)
+
 #define GEN7_ROW_CHICKEN2		0xe4f4
 #define GEN7_ROW_CHICKEN2_GT2		0xf4f4
 #define   DOP_CLOCK_GATING_DISABLE	(1<<0)
@@ -5051,7 +5091,7 @@
 #define   GEN8_CENTROID_PIXEL_OPT_DIS	(1<<8)
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
 
-#define G4X_AUD_VID_DID			(dev_priv->info->display_mmio_offset + 0x62020)
+#define G4X_AUD_VID_DID			(dev_priv->info.display_mmio_offset + 0x62020)
 #define INTEL_AUDIO_DEVCL		0x808629FB
 #define INTEL_AUDIO_DEVBLC		0x80862801
 #define INTEL_AUDIO_DEVCTG		0x80862802
@@ -5435,6 +5475,8 @@
 
 /* SFUSE_STRAP */
 #define SFUSE_STRAP			0xc2014
+#define  SFUSE_STRAP_FUSE_LOCK		(1<<13)
+#define  SFUSE_STRAP_DISPLAY_DISABLED	(1<<7)
 #define  SFUSE_STRAP_DDIB_DETECTED	(1<<2)
 #define  SFUSE_STRAP_DDIC_DETECTED	(1<<1)
 #define  SFUSE_STRAP_DDID_DETECTED	(1<<0)
@@ -5904,11 +5946,11 @@
 #define  READ_DATA_VALID(n)				(1 << (n))
 
 /* For UMS only (deprecated): */
-#define _PALETTE_A (dev_priv->info->display_mmio_offset + 0xa000)
-#define _PALETTE_B (dev_priv->info->display_mmio_offset + 0xa800)
-#define _DPLL_A (dev_priv->info->display_mmio_offset + 0x6014)
-#define _DPLL_B (dev_priv->info->display_mmio_offset + 0x6018)
-#define _DPLL_A_MD (dev_priv->info->display_mmio_offset + 0x601c)
-#define _DPLL_B_MD (dev_priv->info->display_mmio_offset + 0x6020)
+#define _PALETTE_A (dev_priv->info.display_mmio_offset + 0xa000)
+#define _PALETTE_B (dev_priv->info.display_mmio_offset + 0xa800)
+#define _DPLL_A (dev_priv->info.display_mmio_offset + 0x6014)
+#define _DPLL_B (dev_priv->info.display_mmio_offset + 0x6018)
+#define _DPLL_A_MD (dev_priv->info.display_mmio_offset + 0x601c)
+#define _DPLL_B_MD (dev_priv->info.display_mmio_offset + 0x6020)
 
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 6e580c9..b95a380 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -34,15 +34,15 @@
 );
 
 TRACE_EVENT(i915_vma_bind,
-	    TP_PROTO(struct i915_vma *vma, bool mappable),
-	    TP_ARGS(vma, mappable),
+	    TP_PROTO(struct i915_vma *vma, unsigned flags),
+	    TP_ARGS(vma, flags),
 
 	    TP_STRUCT__entry(
 			     __field(struct drm_i915_gem_object *, obj)
 			     __field(struct i915_address_space *, vm)
 			     __field(u32, offset)
 			     __field(u32, size)
-			     __field(bool, mappable)
+			     __field(unsigned, flags)
 			     ),
 
 	    TP_fast_assign(
@@ -50,12 +50,12 @@
 			   __entry->vm = vma->vm;
 			   __entry->offset = vma->node.start;
 			   __entry->size = vma->node.size;
-			   __entry->mappable = mappable;
+			   __entry->flags = flags;
 			   ),
 
 	    TP_printk("obj=%p, offset=%08x size=%x%s vm=%p",
 		      __entry->obj, __entry->offset, __entry->size,
-		      __entry->mappable ? ", mappable" : "",
+		      __entry->flags & PIN_MAPPABLE ? ", mappable" : "",
 		      __entry->vm)
 );
 
@@ -196,26 +196,26 @@
 );
 
 TRACE_EVENT(i915_gem_evict,
-	    TP_PROTO(struct drm_device *dev, u32 size, u32 align, bool mappable),
-	    TP_ARGS(dev, size, align, mappable),
+	    TP_PROTO(struct drm_device *dev, u32 size, u32 align, unsigned flags),
+	    TP_ARGS(dev, size, align, flags),
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, size)
 			     __field(u32, align)
-			     __field(bool, mappable)
+			     __field(unsigned, flags)
 			    ),
 
 	    TP_fast_assign(
 			   __entry->dev = dev->primary->index;
 			   __entry->size = size;
 			   __entry->align = align;
-			   __entry->mappable = mappable;
+			   __entry->flags = flags;
 			  ),
 
 	    TP_printk("dev=%d, size=%d, align=%d %s",
 		      __entry->dev, __entry->size, __entry->align,
-		      __entry->mappable ? ", mappable" : "")
+		      __entry->flags & PIN_MAPPABLE ? ", mappable" : "")
 );
 
 TRACE_EVENT(i915_gem_evict_everything,
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 86b95ca..4867f4c 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -599,14 +599,14 @@
 {
 	struct bdb_mipi *mipi;
 
-	mipi = find_section(bdb, BDB_MIPI);
+	mipi = find_section(bdb, BDB_MIPI_CONFIG);
 	if (!mipi) {
 		DRM_DEBUG_KMS("No MIPI BDB found");
 		return;
 	}
 
 	/* XXX: add more info */
-	dev_priv->vbt.dsi.panel_id = mipi->panel_id;
+	dev_priv->vbt.dsi.panel_id = MIPI_DSI_GENERIC_PANEL_ID;
 }
 
 static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index 282de5e..83b7629 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -104,7 +104,8 @@
 #define BDB_LVDS_LFP_DATA	 42
 #define BDB_LVDS_BACKLIGHT	 43
 #define BDB_LVDS_POWER		 44
-#define BDB_MIPI		 50
+#define BDB_MIPI_CONFIG		 52
+#define BDB_MIPI_SEQUENCE	 53
 #define BDB_SKIP		254 /* VBIOS private block, ignore */
 
 struct bdb_general_features {
@@ -711,44 +712,159 @@
 #define DVO_PORT_DPD	9
 #define DVO_PORT_DPA	10
 
-/* MIPI DSI panel info */
-struct bdb_mipi {
+/* Block 52 contains MIPI Panel info
+ * 6 such enteries will there. Index into correct
+ * entery is based on the panel_index in #40 LFP
+ */
+#define MAX_MIPI_CONFIGURATIONS	6
+
+#define MIPI_DSI_UNDEFINED_PANEL_ID	0
+#define MIPI_DSI_GENERIC_PANEL_ID	1
+
+struct mipi_config {
 	u16 panel_id;
-	u16 bridge_revision;
 
-	/* General params */
-	u32 dithering:1;
-	u32 bpp_pixel_format:1;
+	/* General Params */
+	u32 enable_dithering:1;
 	u32 rsvd1:1;
-	u32 dphy_valid:1;
-	u32 resvd2:28;
+	u32 is_bridge:1;
 
-	u16 port_info;
-	u16 rsvd3:2;
-	u16 num_lanes:2;
-	u16 rsvd4:12;
+	u32 panel_arch_type:2;
+	u32 is_cmd_mode:1;
 
-	/* DSI config */
-	u16 virt_ch_num:2;
-	u16 vtm:2;
-	u16 rsvd5:12;
+#define NON_BURST_SYNC_PULSE	0x1
+#define NON_BURST_SYNC_EVENTS	0x2
+#define BURST_MODE		0x3
+	u32 video_transfer_mode:2;
 
-	u32 dsi_clock;
+	u32 cabc_supported:1;
+	u32 pwm_blc:1;
+
+	/* Bit 13:10 */
+#define PIXEL_FORMAT_RGB565			0x1
+#define PIXEL_FORMAT_RGB666			0x2
+#define PIXEL_FORMAT_RGB666_LOOSELY_PACKED	0x3
+#define PIXEL_FORMAT_RGB888			0x4
+	u32 videomode_color_format:4;
+
+	/* Bit 15:14 */
+#define ENABLE_ROTATION_0	0x0
+#define ENABLE_ROTATION_90	0x1
+#define ENABLE_ROTATION_180	0x2
+#define ENABLE_ROTATION_270	0x3
+	u32 rotation:2;
+	u32 bta_enabled:1;
+	u32 rsvd2:15;
+
+	/* 2 byte Port Description */
+#define DUAL_LINK_NOT_SUPPORTED	0
+#define DUAL_LINK_FRONT_BACK	1
+#define DUAL_LINK_PIXEL_ALT	2
+	u16 dual_link:2;
+	u16 lane_cnt:2;
+	u16 rsvd3:12;
+
+	u16 rsvd4;
+
+	u8 rsvd5[5];
+	u32 dsi_ddr_clk;
 	u32 bridge_ref_clk;
-	u16 rsvd_pwr;
 
-	/* Dphy Params */
-	u32 prepare_cnt:5;
-	u32 rsvd6:3;
+#define  BYTE_CLK_SEL_20MHZ		0
+#define  BYTE_CLK_SEL_10MHZ		1
+#define  BYTE_CLK_SEL_5MHZ		2
+	u8 byte_clk_sel:2;
+
+	u8 rsvd6:6;
+
+	/* DPHY Flags */
+	u16 dphy_param_valid:1;
+	u16 eot_pkt_disabled:1;
+	u16 enable_clk_stop:1;
+	u16 rsvd7:13;
+
+	u32 hs_tx_timeout;
+	u32 lp_rx_timeout;
+	u32 turn_around_timeout;
+	u32 device_reset_timer;
+	u32 master_init_timer;
+	u32 dbi_bw_timer;
+	u32 lp_byte_clk_val;
+
+	/*  4 byte Dphy Params */
+	u32 prepare_cnt:6;
+	u32 rsvd8:2;
 	u32 clk_zero_cnt:8;
 	u32 trail_cnt:5;
-	u32 rsvd7:3;
+	u32 rsvd9:3;
 	u32 exit_zero_cnt:6;
-	u32 rsvd8:2;
+	u32 rsvd10:2;
 
-	u32 hl_switch_cnt;
-	u32 lp_byte_clk;
 	u32 clk_lane_switch_cnt;
+	u32 hl_switch_cnt;
+
+	u32 rsvd11[6];
+
+	/* timings based on dphy spec */
+	u8 tclk_miss;
+	u8 tclk_post;
+	u8 rsvd12;
+	u8 tclk_pre;
+	u8 tclk_prepare;
+	u8 tclk_settle;
+	u8 tclk_term_enable;
+	u8 tclk_trail;
+	u16 tclk_prepare_clkzero;
+	u8 rsvd13;
+	u8 td_term_enable;
+	u8 teot;
+	u8 ths_exit;
+	u8 ths_prepare;
+	u16 ths_prepare_hszero;
+	u8 rsvd14;
+	u8 ths_settle;
+	u8 ths_skip;
+	u8 ths_trail;
+	u8 tinit;
+	u8 tlpx;
+	u8 rsvd15[3];
+
+	/* GPIOs */
+	u8 panel_enable;
+	u8 bl_enable;
+	u8 pwm_enable;
+	u8 reset_r_n;
+	u8 pwr_down_r;
+	u8 stdby_r_n;
+
 } __packed;
 
+/* Block 52 contains MIPI configuration block
+ * 6 * bdb_mipi_config, followed by 6 pps data
+ * block below
+ *
+ * all delays has a unit of 100us
+ */
+struct mipi_pps_data {
+	u16 panel_on_delay;
+	u16 bl_enable_delay;
+	u16 bl_disable_delay;
+	u16 panel_off_delay;
+	u16 panel_power_cycle_delay;
+};
+
+struct bdb_mipi_config {
+	struct mipi_config config[MAX_MIPI_CONFIGURATIONS];
+	struct mipi_pps_data pps[MAX_MIPI_CONFIGURATIONS];
+};
+
+/* Block 53 contains MIPI sequences as needed by the panel
+ * for enabling it. This block can be variable in size and
+ * can be maximum of 6 blocks
+ */
+struct bdb_mipi_sequence {
+	u8 version;
+	u8 data[0];
+};
+
 #endif /* _I830_BIOS_H_ */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 5b444a4..4ef6d69 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -68,8 +68,13 @@
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
+	enum intel_display_power_domain power_domain;
 	u32 tmp;
 
+	power_domain = intel_display_port_power_domain(encoder);
+	if (!intel_display_power_enabled(dev_priv, power_domain))
+		return false;
+
 	tmp = I915_READ(crt->adpa_reg);
 
 	if (!(tmp & ADPA_DAC_ENABLE))
@@ -262,6 +267,10 @@
 	if (HAS_PCH_LPT(dev))
 		pipe_config->pipe_bpp = 24;
 
+	/* FDI must always be 2.7 GHz */
+	if (HAS_DDI(dev))
+		pipe_config->port_clock = 135000 * 2;
+
 	return true;
 }
 
@@ -630,14 +639,22 @@
 intel_crt_detect(struct drm_connector *connector, bool force)
 {
 	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_encoder *intel_encoder = &crt->base;
+	enum intel_display_power_domain power_domain;
 	enum drm_connector_status status;
 	struct intel_load_detect_pipe tmp;
 
+	intel_runtime_pm_get(dev_priv);
+
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n",
 		      connector->base.id, drm_get_connector_name(connector),
 		      force);
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	if (I915_HAS_HOTPLUG(dev)) {
 		/* We can not rely on the HPD pin always being correctly wired
 		 * up, for example many KVM do not pass it through, and so
@@ -645,23 +662,30 @@
 		 */
 		if (intel_crt_detect_hotplug(connector)) {
 			DRM_DEBUG_KMS("CRT detected via hotplug\n");
-			return connector_status_connected;
+			status = connector_status_connected;
+			goto out;
 		} else
 			DRM_DEBUG_KMS("CRT not detected via hotplug\n");
 	}
 
-	if (intel_crt_detect_ddc(connector))
-		return connector_status_connected;
+	if (intel_crt_detect_ddc(connector)) {
+		status = connector_status_connected;
+		goto out;
+	}
 
 	/* Load detection is broken on HPD capable machines. Whoever wants a
 	 * broken monitor (without edid) to work behind a broken kvm (that fails
 	 * to have the right resistors for HP detection) needs to fix this up.
 	 * For now just bail out. */
-	if (I915_HAS_HOTPLUG(dev))
-		return connector_status_disconnected;
+	if (I915_HAS_HOTPLUG(dev)) {
+		status = connector_status_disconnected;
+		goto out;
+	}
 
-	if (!force)
-		return connector->status;
+	if (!force) {
+		status = connector->status;
+		goto out;
+	}
 
 	/* for pre-945g platforms use load detect */
 	if (intel_get_load_detect_pipe(connector, NULL, &tmp)) {
@@ -673,6 +697,10 @@
 	} else
 		status = connector_status_unknown;
 
+out:
+	intel_display_power_put(dev_priv, power_domain);
+	intel_runtime_pm_put(dev_priv);
+
 	return status;
 }
 
@@ -686,17 +714,28 @@
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_encoder *intel_encoder = &crt->base;
+	enum intel_display_power_domain power_domain;
 	int ret;
 	struct i2c_adapter *i2c;
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->vbt.crt_ddc_pin);
 	ret = intel_crt_ddc_get_modes(connector, i2c);
 	if (ret || !IS_G4X(dev))
-		return ret;
+		goto out;
 
 	/* Try to probe digital port for output in DVI-I -> VGA mode. */
 	i2c = intel_gmbus_get_adapter(dev_priv, GMBUS_PORT_DPB);
-	return intel_crt_ddc_get_modes(connector, i2c);
+	ret = intel_crt_ddc_get_modes(connector, i2c);
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static int intel_crt_set_property(struct drm_connector *connector,
@@ -833,6 +872,7 @@
 		crt->base.get_hw_state = intel_crt_get_hw_state;
 	}
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index cd65dd0..e2665e0 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1145,9 +1145,14 @@
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum port port = intel_ddi_get_encoder_port(encoder);
+	enum intel_display_power_domain power_domain;
 	u32 tmp;
 	int i;
 
+	power_domain = intel_display_port_power_domain(encoder);
+	if (!intel_display_power_enabled(dev_priv, power_domain))
+		return false;
+
 	tmp = I915_READ(DDI_BUF_CTL(port));
 
 	if (!(tmp & DDI_BUF_CTL_ENABLE))
@@ -1415,7 +1420,7 @@
 
 	if (lcpll & LCPLL_CD_SOURCE_FCLK) {
 		return 800000;
-	} else if (I915_READ(HSW_FUSE_STRAP) & HSW_CDCLK_LIMIT) {
+	} else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT) {
 		return 450000;
 	} else if (freq == LCPLL_CLK_FREQ_450) {
 		return 450000;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 0f4cbd0..0868afb 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -51,7 +51,10 @@
 
 static int intel_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode,
 			  int x, int y, struct drm_framebuffer *old_fb);
-
+static int intel_framebuffer_init(struct drm_device *dev,
+				  struct intel_framebuffer *ifb,
+				  struct drm_mode_fb_cmd2 *mode_cmd,
+				  struct drm_i915_gem_object *obj);
 
 typedef struct {
 	int	min, max;
@@ -1030,7 +1033,7 @@
 	u32 val;
 
 	/* ILK FDI PLL is always enabled */
-	if (dev_priv->info->gen == 5)
+	if (INTEL_INFO(dev_priv->dev)->gen == 5)
 		return;
 
 	/* On Haswell, DDI ports are responsible for the FDI PLL setup */
@@ -1092,12 +1095,12 @@
 	struct drm_device *dev = dev_priv->dev;
 	bool cur_state;
 
-	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-		cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
-	else if (IS_845G(dev) || IS_I865G(dev))
+	if (IS_845G(dev) || IS_I865G(dev))
 		cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
-	else
+	else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev))
 		cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
+	else
+		cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
 
 	WARN(cur_state != state,
 	     "cursor on pipe %c assertion failure (expected %s, current %s)\n",
@@ -1119,7 +1122,7 @@
 	if (pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE)
 		state = true;
 
-	if (!intel_display_power_enabled(dev_priv->dev,
+	if (!intel_display_power_enabled(dev_priv,
 				POWER_DOMAIN_TRANSCODER(cpu_transcoder))) {
 		cur_state = false;
 	} else {
@@ -1185,16 +1188,16 @@
 				    enum pipe pipe)
 {
 	struct drm_device *dev = dev_priv->dev;
-	int reg, i;
+	int reg, sprite;
 	u32 val;
 
 	if (IS_VALLEYVIEW(dev)) {
-		for (i = 0; i < dev_priv->num_plane; i++) {
-			reg = SPCNTR(pipe, i);
+		for_each_sprite(pipe, sprite) {
+			reg = SPCNTR(pipe, sprite);
 			val = I915_READ(reg);
 			WARN((val & SP_ENABLE),
 			     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
-			     sprite_name(pipe, i), pipe_name(pipe));
+			     sprite_name(pipe, sprite), pipe_name(pipe));
 		}
 	} else if (INTEL_INFO(dev)->gen >= 7) {
 		reg = SPRCTL(pipe);
@@ -1443,7 +1446,7 @@
 	assert_pipe_disabled(dev_priv, crtc->pipe);
 
 	/* No really, not for ILK+ */
-	BUG_ON(dev_priv->info->gen >= 5);
+	BUG_ON(INTEL_INFO(dev)->gen >= 5);
 
 	/* PLL is protected by panel, make sure we can write it */
 	if (IS_MOBILE(dev) && !IS_I830(dev))
@@ -1549,11 +1552,12 @@
  */
 static void ironlake_enable_shared_dpll(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
 
 	/* PCH PLLs only available on ILK, SNB and IVB */
-	BUG_ON(dev_priv->info->gen < 5);
+	BUG_ON(INTEL_INFO(dev)->gen < 5);
 	if (WARN_ON(pll == NULL))
 		return;
 
@@ -1578,11 +1582,12 @@
 
 static void intel_disable_shared_dpll(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
 
 	/* PCH only available on ILK+ */
-	BUG_ON(dev_priv->info->gen < 5);
+	BUG_ON(INTEL_INFO(dev)->gen < 5);
 	if (WARN_ON(pll == NULL))
 	       return;
 
@@ -1617,7 +1622,7 @@
 	uint32_t reg, val, pipeconf_val;
 
 	/* PCH only available on ILK+ */
-	BUG_ON(dev_priv->info->gen < 5);
+	BUG_ON(INTEL_INFO(dev)->gen < 5);
 
 	/* Make sure PCH DPLL is enabled */
 	assert_shared_dpll_enabled(dev_priv,
@@ -1670,7 +1675,7 @@
 	u32 val, pipeconf_val;
 
 	/* PCH only available on ILK+ */
-	BUG_ON(dev_priv->info->gen < 5);
+	BUG_ON(INTEL_INFO(dev_priv->dev)->gen < 5);
 
 	/* FDI must be feeding us bits for PCH ports */
 	assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder);
@@ -1744,21 +1749,16 @@
 
 /**
  * intel_enable_pipe - enable a pipe, asserting requirements
- * @dev_priv: i915 private structure
- * @pipe: pipe to enable
- * @pch_port: on ILK+, is this pipe driving a PCH port or not
+ * @crtc: crtc responsible for the pipe
  *
- * Enable @pipe, making sure that various hardware specific requirements
+ * Enable @crtc's pipe, making sure that various hardware specific requirements
  * are met, if applicable, e.g. PLL enabled, LVDS pairs enabled, etc.
- *
- * @pipe should be %PIPE_A or %PIPE_B.
- *
- * Will wait until the pipe is actually running (i.e. first vblank) before
- * returning.
  */
-static void intel_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe,
-			      bool pch_port, bool dsi)
+static void intel_enable_pipe(struct intel_crtc *crtc)
 {
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum pipe pipe = crtc->pipe;
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
 	enum pipe pch_transcoder;
@@ -1780,12 +1780,12 @@
 	 * need the check.
 	 */
 	if (!HAS_PCH_SPLIT(dev_priv->dev))
-		if (dsi)
+		if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DSI))
 			assert_dsi_pll_enabled(dev_priv);
 		else
 			assert_pll_enabled(dev_priv, pipe);
 	else {
-		if (pch_port) {
+		if (crtc->config.has_pch_encoder) {
 			/* if driving the PCH, we need FDI enabled */
 			assert_fdi_rx_pll_enabled(dev_priv, pch_transcoder);
 			assert_fdi_tx_pll_enabled(dev_priv,
@@ -1796,11 +1796,24 @@
 
 	reg = PIPECONF(cpu_transcoder);
 	val = I915_READ(reg);
-	if (val & PIPECONF_ENABLE)
+	if (val & PIPECONF_ENABLE) {
+		WARN_ON(!(pipe == PIPE_A &&
+			  dev_priv->quirks & QUIRK_PIPEA_FORCE));
 		return;
+	}
 
 	I915_WRITE(reg, val | PIPECONF_ENABLE);
-	intel_wait_for_vblank(dev_priv->dev, pipe);
+	POSTING_READ(reg);
+
+	/*
+	 * There's no guarantee the pipe will really start running now. It
+	 * depends on the Gen, the output type and the relative order between
+	 * pipe and plane enabling. Avoid waiting on HSW+ since it's not
+	 * necessary.
+	 * TODO: audit the previous gens.
+	 */
+	if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
+		intel_wait_for_vblank(dev_priv->dev, pipe);
 }
 
 /**
@@ -1851,7 +1864,8 @@
 void intel_flush_primary_plane(struct drm_i915_private *dev_priv,
 			       enum plane plane)
 {
-	u32 reg = dev_priv->info->gen >= 4 ? DSPSURF(plane) : DSPADDR(plane);
+	struct drm_device *dev = dev_priv->dev;
+	u32 reg = INTEL_INFO(dev)->gen >= 4 ? DSPSURF(plane) : DSPADDR(plane);
 
 	I915_WRITE(reg, I915_READ(reg));
 	POSTING_READ(reg);
@@ -1929,6 +1943,14 @@
 	return false;
 }
 
+static int intel_align_height(struct drm_device *dev, int height, bool tiled)
+{
+	int tile_height;
+
+	tile_height = tiled ? (IS_GEN2(dev) ? 16 : 8) : 1;
+	return ALIGN(height, tile_height);
+}
+
 int
 intel_pin_and_fence_fb_obj(struct drm_device *dev,
 			   struct drm_i915_gem_object *obj,
@@ -2299,31 +2321,23 @@
 	return ret;
 }
 
-static void intel_crtc_update_sarea_pos(struct drm_crtc *crtc, int x, int y)
+static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_master_private *master_priv;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	unsigned long flags;
+	bool pending;
 
-	if (!dev->primary->master)
-		return;
+	if (i915_reset_in_progress(&dev_priv->gpu_error) ||
+	    intel_crtc->reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter))
+		return false;
 
-	master_priv = dev->primary->master->driver_priv;
-	if (!master_priv->sarea_priv)
-		return;
+	spin_lock_irqsave(&dev->event_lock, flags);
+	pending = to_intel_crtc(crtc)->unpin_work != NULL;
+	spin_unlock_irqrestore(&dev->event_lock, flags);
 
-	switch (intel_crtc->pipe) {
-	case 0:
-		master_priv->sarea_priv->pipeA_x = x;
-		master_priv->sarea_priv->pipeA_y = y;
-		break;
-	case 1:
-		master_priv->sarea_priv->pipeB_x = x;
-		master_priv->sarea_priv->pipeB_y = y;
-		break;
-	default:
-		break;
-	}
+	return pending;
 }
 
 static int
@@ -2336,6 +2350,11 @@
 	struct drm_framebuffer *old_fb;
 	int ret;
 
+	if (intel_crtc_has_pending_flip(crtc)) {
+		DRM_ERROR("pipe is still busy with an old pageflip\n");
+		return -EBUSY;
+	}
+
 	/* no fb bound */
 	if (!fb) {
 		DRM_ERROR("No FB bound\n");
@@ -2413,8 +2432,6 @@
 	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 
-	intel_crtc_update_sarea_pos(crtc, x, y);
-
 	return 0;
 }
 
@@ -2963,25 +2980,6 @@
 	udelay(100);
 }
 
-static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	unsigned long flags;
-	bool pending;
-
-	if (i915_reset_in_progress(&dev_priv->gpu_error) ||
-	    intel_crtc->reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter))
-		return false;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-	pending = to_intel_crtc(crtc)->unpin_work != NULL;
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-
-	return pending;
-}
-
 bool intel_has_pending_fb_unpin(struct drm_device *dev)
 {
 	struct intel_crtc *crtc;
@@ -3587,8 +3585,7 @@
 	intel_crtc_load_lut(crtc);
 
 	intel_update_watermarks(crtc);
-	intel_enable_pipe(dev_priv, pipe,
-			  intel_crtc->config.has_pch_encoder, false);
+	intel_enable_pipe(intel_crtc);
 	intel_enable_primary_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
 	intel_crtc_update_cursor(crtc, true);
@@ -3733,8 +3730,7 @@
 	intel_ddi_enable_transcoder_func(crtc);
 
 	intel_update_watermarks(crtc);
-	intel_enable_pipe(dev_priv, pipe,
-			  intel_crtc->config.has_pch_encoder, false);
+	intel_enable_pipe(intel_crtc);
 
 	if (intel_crtc->config.has_pch_encoder)
 		lpt_pch_enable(crtc);
@@ -3748,16 +3744,6 @@
 	 * to change the workaround. */
 	haswell_mode_set_planes_workaround(intel_crtc);
 	haswell_crtc_enable_planes(crtc);
-
-	/*
-	 * There seems to be a race in PCH platform hw (at least on some
-	 * outputs) where an enabled pipe still completes any pageflip right
-	 * away (as if the pipe is off) instead of waiting for vblank. As soon
-	 * as the first vblank happend, everything works as expected. Hence just
-	 * wait for one vblank before returning to avoid strange things
-	 * happening.
-	 */
-	intel_wait_for_vblank(dev, intel_crtc->pipe);
 }
 
 static void ironlake_pfit_disable(struct intel_crtc *crtc)
@@ -3972,6 +3958,117 @@
 	I915_WRITE(BCLRPAT(crtc->pipe), 0);
 }
 
+#define for_each_power_domain(domain, mask)				\
+	for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++)	\
+		if ((1 << (domain)) & (mask))
+
+enum intel_display_power_domain
+intel_display_port_power_domain(struct intel_encoder *intel_encoder)
+{
+	struct drm_device *dev = intel_encoder->base.dev;
+	struct intel_digital_port *intel_dig_port;
+
+	switch (intel_encoder->type) {
+	case INTEL_OUTPUT_UNKNOWN:
+		/* Only DDI platforms should ever use this output type */
+		WARN_ON_ONCE(!HAS_DDI(dev));
+	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_HDMI:
+	case INTEL_OUTPUT_EDP:
+		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+		switch (intel_dig_port->port) {
+		case PORT_A:
+			return POWER_DOMAIN_PORT_DDI_A_4_LANES;
+		case PORT_B:
+			return POWER_DOMAIN_PORT_DDI_B_4_LANES;
+		case PORT_C:
+			return POWER_DOMAIN_PORT_DDI_C_4_LANES;
+		case PORT_D:
+			return POWER_DOMAIN_PORT_DDI_D_4_LANES;
+		default:
+			WARN_ON_ONCE(1);
+			return POWER_DOMAIN_PORT_OTHER;
+		}
+	case INTEL_OUTPUT_ANALOG:
+		return POWER_DOMAIN_PORT_CRT;
+	case INTEL_OUTPUT_DSI:
+		return POWER_DOMAIN_PORT_DSI;
+	default:
+		return POWER_DOMAIN_PORT_OTHER;
+	}
+}
+
+static unsigned long get_crtc_power_domains(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct intel_encoder *intel_encoder;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	enum pipe pipe = intel_crtc->pipe;
+	bool pfit_enabled = intel_crtc->config.pch_pfit.enabled;
+	unsigned long mask;
+	enum transcoder transcoder;
+
+	transcoder = intel_pipe_to_cpu_transcoder(dev->dev_private, pipe);
+
+	mask = BIT(POWER_DOMAIN_PIPE(pipe));
+	mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
+	if (pfit_enabled)
+		mask |= BIT(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
+
+	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
+		mask |= BIT(intel_display_port_power_domain(intel_encoder));
+
+	return mask;
+}
+
+void intel_display_set_init_power(struct drm_i915_private *dev_priv,
+				  bool enable)
+{
+	if (dev_priv->power_domains.init_power_on == enable)
+		return;
+
+	if (enable)
+		intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+	else
+		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+
+	dev_priv->power_domains.init_power_on = enable;
+}
+
+static void modeset_update_crtc_power_domains(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long pipe_domains[I915_MAX_PIPES] = { 0, };
+	struct intel_crtc *crtc;
+
+	/*
+	 * First get all needed power domains, then put all unneeded, to avoid
+	 * any unnecessary toggling of the power wells.
+	 */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+		enum intel_display_power_domain domain;
+
+		if (!crtc->base.enabled)
+			continue;
+
+		pipe_domains[crtc->pipe] = get_crtc_power_domains(&crtc->base);
+
+		for_each_power_domain(domain, pipe_domains[crtc->pipe])
+			intel_display_power_get(dev_priv, domain);
+	}
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+		enum intel_display_power_domain domain;
+
+		for_each_power_domain(domain, crtc->enabled_power_domains)
+			intel_display_power_put(dev_priv, domain);
+
+		crtc->enabled_power_domains = pipe_domains[crtc->pipe];
+	}
+
+	intel_display_set_init_power(dev_priv, false);
+}
+
 int valleyview_get_vco(struct drm_i915_private *dev_priv)
 {
 	int hpll_freq, vco_freq[] = { 800, 1600, 2000, 2400 };
@@ -4132,6 +4229,7 @@
 
 	if (req_cdclk != cur_cdclk)
 		valleyview_set_cdclk(dev, req_cdclk);
+	modeset_update_crtc_power_domains(dev);
 }
 
 static void valleyview_crtc_enable(struct drm_crtc *crtc)
@@ -4169,7 +4267,7 @@
 	intel_crtc_load_lut(crtc);
 
 	intel_update_watermarks(crtc);
-	intel_enable_pipe(dev_priv, pipe, false, is_dsi);
+	intel_enable_pipe(intel_crtc);
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
 	intel_enable_primary_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
@@ -4208,7 +4306,7 @@
 	intel_crtc_load_lut(crtc);
 
 	intel_update_watermarks(crtc);
-	intel_enable_pipe(dev_priv, pipe, false, false);
+	intel_enable_pipe(intel_crtc);
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
 	intel_enable_primary_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
@@ -5256,25 +5354,23 @@
 	pipe_config->requested_mode.hdisplay = pipe_config->pipe_src_w;
 }
 
-static void intel_crtc_mode_from_pipe_config(struct intel_crtc *intel_crtc,
-					     struct intel_crtc_config *pipe_config)
+void intel_mode_from_pipe_config(struct drm_display_mode *mode,
+				 struct intel_crtc_config *pipe_config)
 {
-	struct drm_crtc *crtc = &intel_crtc->base;
+	mode->hdisplay = pipe_config->adjusted_mode.crtc_hdisplay;
+	mode->htotal = pipe_config->adjusted_mode.crtc_htotal;
+	mode->hsync_start = pipe_config->adjusted_mode.crtc_hsync_start;
+	mode->hsync_end = pipe_config->adjusted_mode.crtc_hsync_end;
 
-	crtc->mode.hdisplay = pipe_config->adjusted_mode.crtc_hdisplay;
-	crtc->mode.htotal = pipe_config->adjusted_mode.crtc_htotal;
-	crtc->mode.hsync_start = pipe_config->adjusted_mode.crtc_hsync_start;
-	crtc->mode.hsync_end = pipe_config->adjusted_mode.crtc_hsync_end;
+	mode->vdisplay = pipe_config->adjusted_mode.crtc_vdisplay;
+	mode->vtotal = pipe_config->adjusted_mode.crtc_vtotal;
+	mode->vsync_start = pipe_config->adjusted_mode.crtc_vsync_start;
+	mode->vsync_end = pipe_config->adjusted_mode.crtc_vsync_end;
 
-	crtc->mode.vdisplay = pipe_config->adjusted_mode.crtc_vdisplay;
-	crtc->mode.vtotal = pipe_config->adjusted_mode.crtc_vtotal;
-	crtc->mode.vsync_start = pipe_config->adjusted_mode.crtc_vsync_start;
-	crtc->mode.vsync_end = pipe_config->adjusted_mode.crtc_vsync_end;
+	mode->flags = pipe_config->adjusted_mode.flags;
 
-	crtc->mode.flags = pipe_config->adjusted_mode.flags;
-
-	crtc->mode.clock = pipe_config->adjusted_mode.crtc_clock;
-	crtc->mode.flags |= pipe_config->adjusted_mode.flags;
+	mode->clock = pipe_config->adjusted_mode.crtc_clock;
+	mode->flags |= pipe_config->adjusted_mode.flags;
 }
 
 static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
@@ -5516,6 +5612,10 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
+	if (!intel_display_power_enabled(dev_priv,
+					 POWER_DOMAIN_PIPE(crtc->pipe)))
+		return false;
+
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
@@ -6177,7 +6277,7 @@
 	 * is 2.5%; use 5% for safety's sake.
 	 */
 	u32 bps = target_clock * bpp * 21 / 20;
-	return bps / (link_bw * 8) + 1;
+	return DIV_ROUND_UP(bps, link_bw * 8);
 }
 
 static bool ironlake_needs_fb_cb_tune(struct dpll *dpll, int factor)
@@ -6833,105 +6933,9 @@
 	mutex_unlock(&dev_priv->pc8.lock);
 }
 
-static void hsw_package_c8_gpu_idle(struct drm_i915_private *dev_priv)
-{
-	if (!HAS_PC8(dev_priv->dev))
-		return;
-
-	mutex_lock(&dev_priv->pc8.lock);
-	if (!dev_priv->pc8.gpu_idle) {
-		dev_priv->pc8.gpu_idle = true;
-		__hsw_enable_package_c8(dev_priv);
-	}
-	mutex_unlock(&dev_priv->pc8.lock);
-}
-
-static void hsw_package_c8_gpu_busy(struct drm_i915_private *dev_priv)
-{
-	if (!HAS_PC8(dev_priv->dev))
-		return;
-
-	mutex_lock(&dev_priv->pc8.lock);
-	if (dev_priv->pc8.gpu_idle) {
-		dev_priv->pc8.gpu_idle = false;
-		__hsw_disable_package_c8(dev_priv);
-	}
-	mutex_unlock(&dev_priv->pc8.lock);
-}
-
-#define for_each_power_domain(domain, mask)				\
-	for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++)	\
-		if ((1 << (domain)) & (mask))
-
-static unsigned long get_pipe_power_domains(struct drm_device *dev,
-					    enum pipe pipe, bool pfit_enabled)
-{
-	unsigned long mask;
-	enum transcoder transcoder;
-
-	transcoder = intel_pipe_to_cpu_transcoder(dev->dev_private, pipe);
-
-	mask = BIT(POWER_DOMAIN_PIPE(pipe));
-	mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
-	if (pfit_enabled)
-		mask |= BIT(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
-
-	return mask;
-}
-
-void intel_display_set_init_power(struct drm_device *dev, bool enable)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (dev_priv->power_domains.init_power_on == enable)
-		return;
-
-	if (enable)
-		intel_display_power_get(dev, POWER_DOMAIN_INIT);
-	else
-		intel_display_power_put(dev, POWER_DOMAIN_INIT);
-
-	dev_priv->power_domains.init_power_on = enable;
-}
-
-static void modeset_update_power_wells(struct drm_device *dev)
-{
-	unsigned long pipe_domains[I915_MAX_PIPES] = { 0, };
-	struct intel_crtc *crtc;
-
-	/*
-	 * First get all needed power domains, then put all unneeded, to avoid
-	 * any unnecessary toggling of the power wells.
-	 */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
-		enum intel_display_power_domain domain;
-
-		if (!crtc->base.enabled)
-			continue;
-
-		pipe_domains[crtc->pipe] = get_pipe_power_domains(dev,
-						crtc->pipe,
-						crtc->config.pch_pfit.enabled);
-
-		for_each_power_domain(domain, pipe_domains[crtc->pipe])
-			intel_display_power_get(dev, domain);
-	}
-
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
-		enum intel_display_power_domain domain;
-
-		for_each_power_domain(domain, crtc->enabled_power_domains)
-			intel_display_power_put(dev, domain);
-
-		crtc->enabled_power_domains = pipe_domains[crtc->pipe];
-	}
-
-	intel_display_set_init_power(dev, false);
-}
-
 static void haswell_modeset_global_resources(struct drm_device *dev)
 {
-	modeset_update_power_wells(dev);
+	modeset_update_crtc_power_domains(dev);
 	hsw_update_package_c8(dev);
 }
 
@@ -6982,6 +6986,10 @@
 	enum intel_display_power_domain pfit_domain;
 	uint32_t tmp;
 
+	if (!intel_display_power_enabled(dev_priv,
+					 POWER_DOMAIN_PIPE(crtc->pipe)))
+		return false;
+
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
@@ -7007,7 +7015,7 @@
 			pipe_config->cpu_transcoder = TRANSCODER_EDP;
 	}
 
-	if (!intel_display_power_enabled(dev,
+	if (!intel_display_power_enabled(dev_priv,
 			POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder)))
 		return false;
 
@@ -7035,7 +7043,7 @@
 	intel_get_pipe_timings(crtc, pipe_config);
 
 	pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
-	if (intel_display_power_enabled(dev, pfit_domain))
+	if (intel_display_power_enabled(dev_priv, pfit_domain))
 		ironlake_get_pfit_config(crtc, pipe_config);
 
 	if (IS_HASWELL(dev))
@@ -7570,18 +7578,18 @@
 		return -ENOENT;
 
 	if (obj->base.size < width * height * 4) {
-		DRM_ERROR("buffer is to small\n");
+		DRM_DEBUG_KMS("buffer is to small\n");
 		ret = -ENOMEM;
 		goto fail;
 	}
 
 	/* we only need to pin inside GTT if cursor is non-phy */
 	mutex_lock(&dev->struct_mutex);
-	if (!dev_priv->info->cursor_needs_physical) {
+	if (!INTEL_INFO(dev)->cursor_needs_physical) {
 		unsigned alignment;
 
 		if (obj->tiling_mode) {
-			DRM_ERROR("cursor cannot be tiled\n");
+			DRM_DEBUG_KMS("cursor cannot be tiled\n");
 			ret = -EINVAL;
 			goto fail_locked;
 		}
@@ -7597,13 +7605,13 @@
 
 		ret = i915_gem_object_pin_to_display_plane(obj, alignment, NULL);
 		if (ret) {
-			DRM_ERROR("failed to move cursor bo into the GTT\n");
+			DRM_DEBUG_KMS("failed to move cursor bo into the GTT\n");
 			goto fail_locked;
 		}
 
 		ret = i915_gem_object_put_fence(obj);
 		if (ret) {
-			DRM_ERROR("failed to release fence for cursor");
+			DRM_DEBUG_KMS("failed to release fence for cursor");
 			goto fail_unpin;
 		}
 
@@ -7614,7 +7622,7 @@
 						  (intel_crtc->pipe == 0) ? I915_GEM_PHYS_CURSOR_0 : I915_GEM_PHYS_CURSOR_1,
 						  align);
 		if (ret) {
-			DRM_ERROR("failed to attach phys object\n");
+			DRM_DEBUG_KMS("failed to attach phys object\n");
 			goto fail_locked;
 		}
 		addr = obj->phys_obj->handle->busaddr;
@@ -7625,7 +7633,7 @@
 
  finish:
 	if (intel_crtc->cursor_bo) {
-		if (dev_priv->info->cursor_needs_physical) {
+		if (INTEL_INFO(dev)->cursor_needs_physical) {
 			if (intel_crtc->cursor_bo != obj)
 				i915_gem_detach_phys_object(dev, intel_crtc->cursor_bo);
 		} else
@@ -7687,10 +7695,10 @@
 		 704, 832, 0, 480, 489, 491, 520, 0, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 };
 
-static struct drm_framebuffer *
-intel_framebuffer_create(struct drm_device *dev,
-			 struct drm_mode_fb_cmd2 *mode_cmd,
-			 struct drm_i915_gem_object *obj)
+struct drm_framebuffer *
+__intel_framebuffer_create(struct drm_device *dev,
+			   struct drm_mode_fb_cmd2 *mode_cmd,
+			   struct drm_i915_gem_object *obj)
 {
 	struct intel_framebuffer *intel_fb;
 	int ret;
@@ -7701,12 +7709,7 @@
 		return ERR_PTR(-ENOMEM);
 	}
 
-	ret = i915_mutex_lock_interruptible(dev);
-	if (ret)
-		goto err;
-
 	ret = intel_framebuffer_init(dev, intel_fb, mode_cmd, obj);
-	mutex_unlock(&dev->struct_mutex);
 	if (ret)
 		goto err;
 
@@ -7718,6 +7721,23 @@
 	return ERR_PTR(ret);
 }
 
+static struct drm_framebuffer *
+intel_framebuffer_create(struct drm_device *dev,
+			 struct drm_mode_fb_cmd2 *mode_cmd,
+			 struct drm_i915_gem_object *obj)
+{
+	struct drm_framebuffer *fb;
+	int ret;
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret)
+		return ERR_PTR(ret);
+	fb = __intel_framebuffer_create(dev, mode_cmd, obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	return fb;
+}
+
 static u32
 intel_framebuffer_pitch_for_width(int width, int bpp)
 {
@@ -7763,14 +7783,16 @@
 	struct drm_i915_gem_object *obj;
 	struct drm_framebuffer *fb;
 
-	if (dev_priv->fbdev == NULL)
+	if (!dev_priv->fbdev)
 		return NULL;
 
-	obj = dev_priv->fbdev->ifb.obj;
-	if (obj == NULL)
+	if (!dev_priv->fbdev->fb)
 		return NULL;
 
-	fb = &dev_priv->fbdev->ifb.base;
+	obj = dev_priv->fbdev->fb->obj;
+	BUG_ON(!obj);
+
+	fb = &dev_priv->fbdev->fb->base;
 	if (fb->pitches[0] < intel_framebuffer_pitch_for_width(mode->hdisplay,
 							       fb->bits_per_pixel))
 		return NULL;
@@ -8199,8 +8221,12 @@
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	hsw_package_c8_gpu_busy(dev_priv);
+	if (dev_priv->mm.busy)
+		return;
+
+	hsw_disable_package_c8(dev_priv);
 	i915_update_gfx_val(dev_priv);
+	dev_priv->mm.busy = true;
 }
 
 void intel_mark_idle(struct drm_device *dev)
@@ -8208,10 +8234,13 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 
-	hsw_package_c8_gpu_idle(dev_priv);
+	if (!dev_priv->mm.busy)
+		return;
+
+	dev_priv->mm.busy = false;
 
 	if (!i915.powersave)
-		return;
+		goto out;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		if (!crtc->fb)
@@ -8220,8 +8249,11 @@
 		intel_decrease_pllclock(crtc);
 	}
 
-	if (dev_priv->info->gen >= 6)
+	if (INTEL_INFO(dev)->gen >= 6)
 		gen6_rps_idle(dev->dev_private);
+
+out:
+	hsw_enable_package_c8(dev_priv);
 }
 
 void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
@@ -8685,6 +8717,9 @@
 	     fb->pitches[0] != crtc->fb->pitches[0]))
 		return -EINVAL;
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		goto out_hang;
+
 	work = kzalloc(sizeof(*work), GFP_KERNEL);
 	if (work == NULL)
 		return -ENOMEM;
@@ -8759,6 +8794,13 @@
 free_work:
 	kfree(work);
 
+	if (ret == -EIO) {
+out_hang:
+		intel_crtc_wait_for_pending_flips(crtc);
+		ret = intel_pipe_set_base(crtc, crtc->x, crtc->y, fb);
+		if (ret == 0 && event)
+			drm_send_vblank_event(dev, intel_crtc->pipe, event);
+	}
 	return ret;
 }
 
@@ -10384,8 +10426,7 @@
 	if ((I915_READ(DP_A) & DP_DETECTED) == 0)
 		return false;
 
-	if (IS_GEN5(dev) &&
-	    (I915_READ(ILK_DISPLAY_CHICKEN_FUSES) & ILK_eDP_A_DISABLE))
+	if (IS_GEN5(dev) && (I915_READ(FUSE_STRAP) & ILK_eDP_A_DISABLE))
 		return false;
 
 	return true;
@@ -10538,18 +10579,13 @@
 	drm_helper_move_panel_connectors_to_head(dev);
 }
 
-void intel_framebuffer_fini(struct intel_framebuffer *fb)
-{
-	drm_framebuffer_cleanup(&fb->base);
-	WARN_ON(!fb->obj->framebuffer_references--);
-	drm_gem_object_unreference_unlocked(&fb->obj->base);
-}
-
 static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 
-	intel_framebuffer_fini(intel_fb);
+	drm_framebuffer_cleanup(fb);
+	WARN_ON(!intel_fb->obj->framebuffer_references--);
+	drm_gem_object_unreference_unlocked(&intel_fb->obj->base);
 	kfree(intel_fb);
 }
 
@@ -10568,12 +10604,12 @@
 	.create_handle = intel_user_framebuffer_create_handle,
 };
 
-int intel_framebuffer_init(struct drm_device *dev,
-			   struct intel_framebuffer *intel_fb,
-			   struct drm_mode_fb_cmd2 *mode_cmd,
-			   struct drm_i915_gem_object *obj)
+static int intel_framebuffer_init(struct drm_device *dev,
+				  struct intel_framebuffer *intel_fb,
+				  struct drm_mode_fb_cmd2 *mode_cmd,
+				  struct drm_i915_gem_object *obj)
 {
-	int aligned_height, tile_height;
+	int aligned_height;
 	int pitch_limit;
 	int ret;
 
@@ -10667,9 +10703,8 @@
 	if (mode_cmd->offsets[0] != 0)
 		return -EINVAL;
 
-	tile_height = IS_GEN2(dev) ? 16 : 8;
-	aligned_height = ALIGN(mode_cmd->height,
-			       obj->tiling_mode ? tile_height : 1);
+	aligned_height = intel_align_height(dev, mode_cmd->height,
+					    obj->tiling_mode);
 	/* FIXME drm helper for size checks (especially planar formats)? */
 	if (obj->base.size < aligned_height * mode_cmd->pitches[0])
 		return -EINVAL;
@@ -11010,7 +11045,8 @@
 void intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int i, j, ret;
+	int sprite, ret;
+	enum pipe pipe;
 
 	drm_mode_config_init(dev);
 
@@ -11047,13 +11083,13 @@
 		      INTEL_INFO(dev)->num_pipes,
 		      INTEL_INFO(dev)->num_pipes > 1 ? "s" : "");
 
-	for_each_pipe(i) {
-		intel_crtc_init(dev, i);
-		for (j = 0; j < dev_priv->num_plane; j++) {
-			ret = intel_plane_init(dev, i, j);
+	for_each_pipe(pipe) {
+		intel_crtc_init(dev, pipe);
+		for_each_sprite(pipe, sprite) {
+			ret = intel_plane_init(dev, pipe, sprite);
 			if (ret)
 				DRM_DEBUG_KMS("pipe %c sprite %c init failed: %d\n",
-					      pipe_name(i), sprite_name(i, j), ret);
+					      pipe_name(pipe), sprite_name(pipe, sprite), ret);
 		}
 	}
 
@@ -11069,6 +11105,10 @@
 
 	/* Just in case the BIOS is doing something questionable. */
 	intel_disable_fbc(dev);
+
+	mutex_lock(&dev->mode_config.mutex);
+	intel_modeset_setup_hw_state(dev, false);
+	mutex_unlock(&dev->mode_config.mutex);
 }
 
 static void
@@ -11251,11 +11291,21 @@
 	 * the crtc fixup. */
 }
 
-void i915_redisable_vga(struct drm_device *dev)
+void i915_redisable_vga_power_on(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 vga_reg = i915_vgacntrl_reg(dev);
 
+	if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
+		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
+		i915_disable_vga(dev);
+	}
+}
+
+void i915_redisable_vga(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
 	/* This function can be called both from intel_modeset_setup_hw_state or
 	 * at a very early point in our resume sequence, where the power well
 	 * structures are not yet restored. Since this function is at a very
@@ -11263,14 +11313,10 @@
 	 * level, just check if the power well is enabled instead of trying to
 	 * follow the "don't touch the power well if we don't need it" policy
 	 * the rest of the driver uses. */
-	if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) &&
-	    (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE_ENABLED) == 0)
+	if (!intel_display_power_enabled(dev_priv, POWER_DOMAIN_VGA))
 		return;
 
-	if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
-		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
-		i915_disable_vga(dev);
-	}
+	i915_redisable_vga_power_on(dev);
 }
 
 static void intel_modeset_readout_hw_state(struct drm_device *dev)
@@ -11375,8 +11421,7 @@
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
 			    base.head) {
 		if (crtc->active && i915.fastboot) {
-			intel_crtc_mode_from_pipe_config(crtc, &crtc->config);
-
+			intel_mode_from_pipe_config(&crtc->base.mode, &crtc->config);
 			DRM_DEBUG_KMS("[CRTC:%d] found active mode: ",
 				      crtc->base.base.id);
 			drm_mode_debug_printmodeline(&crtc->base.mode);
@@ -11436,10 +11481,14 @@
 	intel_modeset_init_hw(dev);
 
 	intel_setup_overlay(dev);
+}
 
-	mutex_lock(&dev->mode_config.mutex);
-	intel_modeset_setup_hw_state(dev, false);
-	mutex_unlock(&dev->mode_config.mutex);
+void intel_connector_unregister(struct intel_connector *intel_connector)
+{
+	struct drm_connector *connector = &intel_connector->base;
+
+	intel_panel_destroy_backlight(connector);
+	drm_sysfs_connector_remove(connector);
 }
 
 void intel_modeset_cleanup(struct drm_device *dev)
@@ -11486,8 +11535,10 @@
 
 	/* destroy the backlight and sysfs files before encoders/connectors */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		intel_panel_destroy_backlight(connector);
-		drm_sysfs_connector_remove(connector);
+		struct intel_connector *intel_connector;
+
+		intel_connector = to_intel_connector(connector);
+		intel_connector->unregister(intel_connector);
 	}
 
 	drm_mode_config_cleanup(dev);
@@ -11520,12 +11571,24 @@
 	unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
 	u16 gmch_ctrl;
 
-	pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl);
+	if (pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl)) {
+		DRM_ERROR("failed to read control word\n");
+		return -EIO;
+	}
+
+	if (!!(gmch_ctrl & INTEL_GMCH_VGA_DISABLE) == !state)
+		return 0;
+
 	if (state)
 		gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE;
 	else
 		gmch_ctrl |= INTEL_GMCH_VGA_DISABLE;
-	pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl);
+
+	if (pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl)) {
+		DRM_ERROR("failed to write control word\n");
+		return -EIO;
+	}
+
 	return 0;
 }
 
@@ -11597,7 +11660,8 @@
 
 	for_each_pipe(i) {
 		error->pipe[i].power_domain_on =
-			intel_display_power_enabled_sw(dev, POWER_DOMAIN_PIPE(i));
+			intel_display_power_enabled_sw(dev_priv,
+						       POWER_DOMAIN_PIPE(i));
 		if (!error->pipe[i].power_domain_on)
 			continue;
 
@@ -11635,7 +11699,7 @@
 		enum transcoder cpu_transcoder = transcoders[i];
 
 		error->transcoder[i].power_domain_on =
-			intel_display_power_enabled_sw(dev,
+			intel_display_power_enabled_sw(dev_priv,
 				POWER_DOMAIN_TRANSCODER(cpu_transcoder));
 		if (!error->transcoder[i].power_domain_on)
 			continue;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index bd1df50..49d12d3 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -784,6 +784,16 @@
 	return ret;
 }
 
+static void
+intel_dp_connector_unregister(struct intel_connector *intel_connector)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(&intel_connector->base);
+
+	sysfs_remove_link(&intel_connector->base.kdev->kobj,
+			  intel_dp->adapter.dev.kobj.name);
+	intel_connector_unregister(intel_connector);
+}
+
 static int
 intel_dp_i2c_init(struct intel_dp *intel_dp,
 		  struct intel_connector *intel_connector, const char *name)
@@ -801,9 +811,19 @@
 	strncpy(intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
 	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
 	intel_dp->adapter.algo_data = &intel_dp->algo;
-	intel_dp->adapter.dev.parent = intel_connector->base.kdev;
+	intel_dp->adapter.dev.parent = intel_connector->base.dev->dev;
 
 	ret = i2c_dp_aux_add_bus(&intel_dp->adapter);
+	if (ret < 0)
+		return ret;
+
+	ret = sysfs_create_link(&intel_connector->base.kdev->kobj,
+				&intel_dp->adapter.dev.kobj,
+				intel_dp->adapter.dev.kobj.name);
+
+	if (ret < 0)
+		i2c_del_adapter(&intel_dp->adapter);
+
 	return ret;
 }
 
@@ -896,8 +916,8 @@
 		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
 						   bpp);
 
-		for (clock = 0; clock <= max_clock; clock++) {
-			for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
+		for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
+			for (clock = 0; clock <= max_clock; clock++) {
 				link_clock = drm_dp_bw_code_to_link_rate(bws[clock]);
 				link_avail = intel_dp_max_data_rate(link_clock,
 								    lane_count);
@@ -1313,7 +1333,8 @@
 	pp = ironlake_get_pp_control(intel_dp);
 	/* 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 | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_FORCE_VDD |
+		EDP_BLC_ENABLE);
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
@@ -1465,7 +1486,14 @@
 	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 tmp = I915_READ(intel_dp->output_reg);
+	enum intel_display_power_domain power_domain;
+	u32 tmp;
+
+	power_domain = intel_display_port_power_domain(encoder);
+	if (!intel_display_power_enabled(dev_priv, power_domain))
+		return false;
+
+	tmp = I915_READ(intel_dp->output_reg);
 
 	if (!(tmp & DP_PORT_EN))
 		return false;
@@ -1848,9 +1876,11 @@
 
 	/* Make sure the panel is off before trying to change the mode. But also
 	 * ensure that we have vdd while we switch off the panel. */
+	edp_panel_vdd_on(intel_dp);
 	intel_edp_backlight_off(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 	intel_edp_panel_off(intel_dp);
+	edp_panel_vdd_off(intel_dp, true);
 
 	/* cpu edp my only be disable _after_ the cpu pipe/plane is disabled. */
 	if (!(port == PORT_A || IS_VALLEYVIEW(dev)))
@@ -3204,10 +3234,14 @@
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum drm_connector_status status;
+	enum intel_display_power_domain power_domain;
 	struct edid *edid = NULL;
 
 	intel_runtime_pm_get(dev_priv);
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, drm_get_connector_name(connector));
 
@@ -3238,21 +3272,32 @@
 	status = connector_status_connected;
 
 out:
+	intel_display_power_put(dev_priv, power_domain);
+
 	intel_runtime_pm_put(dev_priv);
+
 	return status;
 }
 
 static int intel_dp_get_modes(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	int ret;
 
 	/* We should parse the EDID data and find out if it has an audio sink
 	 */
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	ret = intel_dp_get_edid_modes(connector, &intel_dp->adapter);
+	intel_display_power_put(dev_priv, power_domain);
 	if (ret)
 		return ret;
 
@@ -3273,15 +3318,25 @@
 intel_dp_detect_audio(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
+	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	struct edid *edid;
 	bool has_audio = false;
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	edid = intel_dp_get_edid(connector, &intel_dp->adapter);
 	if (edid) {
 		has_audio = drm_detect_monitor_audio(edid);
 		kfree(edid);
 	}
 
+	intel_display_power_put(dev_priv, power_domain);
+
 	return has_audio;
 }
 
@@ -3739,7 +3794,7 @@
 			fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
 	}
 
-	intel_panel_init(&intel_connector->panel, fixed_mode);
+	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
 	intel_panel_setup_backlight(connector);
 
 	return true;
@@ -3808,6 +3863,7 @@
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_dp_connector_unregister;
 
 	intel_dp->aux_ch_ctl_reg = intel_dp->output_reg + 0x10;
 	if (HAS_DDI(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 44067bc..9c70905 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -110,7 +110,7 @@
 
 struct intel_fbdev {
 	struct drm_fb_helper helper;
-	struct intel_framebuffer ifb;
+	struct intel_framebuffer *fb;
 	struct list_head fbdev_list;
 	struct drm_display_mode *our_mode;
 };
@@ -187,6 +187,14 @@
 	 * and active (i.e. dpms ON state). */
 	bool (*get_hw_state)(struct intel_connector *);
 
+	/*
+	 * Removes all interfaces through which the connector is accessible
+	 * - like sysfs, debugfs entries -, so that no new operations can be
+	 * started on the connector. Also makes sure all currently pending
+	 * operations finish before returing.
+	 */
+	void (*unregister)(struct intel_connector *);
+
 	/* Panel info for eDP and LVDS */
 	struct intel_panel panel;
 
@@ -601,6 +609,8 @@
 /* i915_irq.c */
 bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 					   enum pipe pipe, bool enable);
+bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
+					     enum pipe pipe, bool enable);
 bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 					   enum transcoder pch_transcoder,
 					   bool enable);
@@ -681,11 +691,10 @@
 			       struct drm_i915_gem_object *obj,
 			       struct intel_ring_buffer *pipelined);
 void intel_unpin_fb_obj(struct drm_i915_gem_object *obj);
-int intel_framebuffer_init(struct drm_device *dev,
-			   struct intel_framebuffer *ifb,
+struct drm_framebuffer *
+__intel_framebuffer_create(struct drm_device *dev,
 			   struct drm_mode_fb_cmd2 *mode_cmd,
 			   struct drm_i915_gem_object *obj);
-void intel_framebuffer_fini(struct intel_framebuffer *fb);
 void intel_prepare_page_flip(struct drm_device *dev, int plane);
 void intel_finish_page_flip(struct drm_device *dev, int pipe);
 void intel_finish_page_flip_plane(struct drm_device *dev, int plane);
@@ -725,8 +734,12 @@
 bool intel_crtc_active(struct drm_crtc *crtc);
 void hsw_enable_ips(struct intel_crtc *crtc);
 void hsw_disable_ips(struct intel_crtc *crtc);
-void intel_display_set_init_power(struct drm_device *dev, bool enable);
+void intel_display_set_init_power(struct drm_i915_private *dev, bool enable);
+enum intel_display_power_domain
+intel_display_port_power_domain(struct intel_encoder *intel_encoder);
 int valleyview_get_vco(struct drm_i915_private *dev_priv);
+void intel_mode_from_pipe_config(struct drm_display_mode *mode,
+				 struct intel_crtc_config *pipe_config);
 
 /* intel_dp.c */
 void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
@@ -824,7 +837,8 @@
 
 /* intel_panel.c */
 int intel_panel_init(struct intel_panel *panel,
-		     struct drm_display_mode *fixed_mode);
+		     struct drm_display_mode *fixed_mode,
+		     struct drm_display_mode *downclock_mode);
 void intel_panel_fini(struct intel_panel *panel);
 void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode,
 			    struct drm_display_mode *adjusted_mode);
@@ -861,18 +875,17 @@
 void intel_update_fbc(struct drm_device *dev);
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
 void intel_gpu_ips_teardown(void);
-int intel_power_domains_init(struct drm_device *dev);
-void intel_power_domains_remove(struct drm_device *dev);
-bool intel_display_power_enabled(struct drm_device *dev,
+int intel_power_domains_init(struct drm_i915_private *);
+void intel_power_domains_remove(struct drm_i915_private *);
+bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
 				 enum intel_display_power_domain domain);
-bool intel_display_power_enabled_sw(struct drm_device *dev,
+bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv,
 				    enum intel_display_power_domain domain);
-void intel_display_power_get(struct drm_device *dev,
+void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
-void intel_display_power_put(struct drm_device *dev,
+void intel_display_power_put(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
-void intel_power_domains_init_hw(struct drm_device *dev);
-void intel_set_power_well(struct drm_device *dev, bool enable);
+void intel_power_domains_init_hw(struct drm_i915_private *dev_priv);
 void intel_enable_gt_powersave(struct drm_device *dev);
 void intel_disable_gt_powersave(struct drm_device *dev);
 void ironlake_teardown_rc6(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index fabbf0d..cf7322e 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -243,11 +243,16 @@
 				   enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	u32 port, func;
 	enum pipe p;
 
 	DRM_DEBUG_KMS("\n");
 
+	power_domain = intel_display_port_power_domain(encoder);
+	if (!intel_display_power_enabled(dev_priv, power_domain))
+		return false;
+
 	/* XXX: this only works for one DSI output */
 	for (p = PIPE_A; p <= PIPE_B; p++) {
 		port = I915_READ(MIPI_PORT_CTRL(p));
@@ -488,8 +493,19 @@
 intel_dsi_detect(struct drm_connector *connector, bool force)
 {
 	struct intel_dsi *intel_dsi = intel_attached_dsi(connector);
+	struct intel_encoder *intel_encoder = &intel_dsi->base;
+	enum intel_display_power_domain power_domain;
+	enum drm_connector_status connector_status;
+	struct drm_i915_private *dev_priv = intel_encoder->base.dev->dev_private;
+
 	DRM_DEBUG_KMS("\n");
-	return intel_dsi->dev.dev_ops->detect(&intel_dsi->dev);
+	power_domain = intel_display_port_power_domain(intel_encoder);
+
+	intel_display_power_get(dev_priv, power_domain);
+	connector_status = intel_dsi->dev.dev_ops->detect(&intel_dsi->dev);
+	intel_display_power_put(dev_priv, power_domain);
+
+	return connector_status;
 }
 
 static int intel_dsi_get_modes(struct drm_connector *connector)
@@ -586,6 +602,7 @@
 	intel_encoder->get_config = intel_dsi_get_config;
 
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	for (i = 0; i < ARRAY_SIZE(intel_dsi_devices); i++) {
 		dsi = &intel_dsi_devices[i];
@@ -624,7 +641,7 @@
 	}
 
 	fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
-	intel_panel_init(&intel_connector->panel, fixed_mode);
+	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
 
 	return true;
 
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index eeff998..86eeb8b7 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -477,6 +477,7 @@
 	intel_encoder->compute_config = intel_dvo_compute_config;
 	intel_encoder->mode_set = intel_dvo_mode_set;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	/* Now, try to find a controller */
 	for (i = 0; i < ARRAY_SIZE(intel_dvo_devices); i++) {
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index d6a8a71..6b5beed 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -62,6 +62,7 @@
 {
 	struct intel_fbdev *ifbdev =
 		container_of(helper, struct intel_fbdev, helper);
+	struct drm_framebuffer *fb;
 	struct drm_device *dev = helper->dev;
 	struct drm_mode_fb_cmd2 mode_cmd = {};
 	struct drm_i915_gem_object *obj;
@@ -93,13 +94,17 @@
 	/* Flush everything out, we'll be doing GTT only from now on */
 	ret = intel_pin_and_fence_fb_obj(dev, obj, NULL);
 	if (ret) {
-		DRM_ERROR("failed to pin fb: %d\n", ret);
+		DRM_ERROR("failed to pin obj: %d\n", ret);
 		goto out_unref;
 	}
 
-	ret = intel_framebuffer_init(dev, &ifbdev->ifb, &mode_cmd, obj);
-	if (ret)
+	fb = __intel_framebuffer_create(dev, &mode_cmd, obj);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto out_unpin;
+	}
+
+	ifbdev->fb = to_intel_framebuffer(fb);
 
 	return 0;
 
@@ -116,7 +121,7 @@
 {
 	struct intel_fbdev *ifbdev =
 		container_of(helper, struct intel_fbdev, helper);
-	struct intel_framebuffer *intel_fb = &ifbdev->ifb;
+	struct intel_framebuffer *intel_fb = ifbdev->fb;
 	struct drm_device *dev = helper->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct fb_info *info;
@@ -126,11 +131,12 @@
 
 	mutex_lock(&dev->struct_mutex);
 
-	if (!intel_fb->obj) {
+	if (!intel_fb || WARN_ON(!intel_fb->obj)) {
 		DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n");
 		ret = intelfb_alloc(helper, sizes);
 		if (ret)
 			goto out_unlock;
+		intel_fb = ifbdev->fb;
 	} else {
 		DRM_DEBUG_KMS("re-using BIOS fb\n");
 		sizes->fb_width = intel_fb->base.width;
@@ -148,7 +154,7 @@
 
 	info->par = helper;
 
-	fb = &ifbdev->ifb.base;
+	fb = &ifbdev->fb->base;
 
 	ifbdev->helper.fb = fb;
 	ifbdev->helper.fbdev = info;
@@ -194,7 +200,7 @@
 	 * If the object is stolen however, it will be full of whatever
 	 * garbage was left in there.
 	 */
-	if (ifbdev->ifb.obj->stolen)
+	if (ifbdev->fb->obj->stolen)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
@@ -236,7 +242,193 @@
 	*blue = intel_crtc->lut_b[regno] << 8;
 }
 
+static struct drm_fb_helper_crtc *
+intel_fb_helper_crtc(struct drm_fb_helper *fb_helper, struct drm_crtc *crtc)
+{
+	int i;
+
+	for (i = 0; i < fb_helper->crtc_count; i++)
+		if (fb_helper->crtc_info[i].mode_set.crtc == crtc)
+			return &fb_helper->crtc_info[i];
+
+	return NULL;
+}
+
+/*
+ * Try to read the BIOS display configuration and use it for the initial
+ * fb configuration.
+ *
+ * The BIOS or boot loader will generally create an initial display
+ * configuration for us that includes some set of active pipes and displays.
+ * This routine tries to figure out which pipes and connectors are active
+ * and stuffs them into the crtcs and modes array given to us by the
+ * drm_fb_helper code.
+ *
+ * The overall sequence is:
+ *   intel_fbdev_init - from driver load
+ *     intel_fbdev_init_bios - initialize the intel_fbdev using BIOS data
+ *     drm_fb_helper_init - build fb helper structs
+ *     drm_fb_helper_single_add_all_connectors - more fb helper structs
+ *   intel_fbdev_initial_config - apply the config
+ *     drm_fb_helper_initial_config - call ->probe then register_framebuffer()
+ *         drm_setup_crtcs - build crtc config for fbdev
+ *           intel_fb_initial_config - find active connectors etc
+ *         drm_fb_helper_single_fb_probe - set up fbdev
+ *           intelfb_create - re-use or alloc fb, build out fbdev structs
+ *
+ * Note that we don't make special consideration whether we could actually
+ * switch to the selected modes without a full modeset. E.g. when the display
+ * is in VGA mode we need to recalculate watermarks and set a new high-res
+ * framebuffer anyway.
+ */
+static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
+				    struct drm_fb_helper_crtc **crtcs,
+				    struct drm_display_mode **modes,
+				    bool *enabled, int width, int height)
+{
+	struct drm_device *dev = fb_helper->dev;
+	int i, j;
+	bool *save_enabled;
+	bool fallback = true;
+	int num_connectors_enabled = 0;
+	int num_connectors_detected = 0;
+
+	/*
+	 * If the user specified any force options, just bail here
+	 * and use that config.
+	 */
+	for (i = 0; i < fb_helper->connector_count; i++) {
+		struct drm_fb_helper_connector *fb_conn;
+		struct drm_connector *connector;
+
+		fb_conn = fb_helper->connector_info[i];
+		connector = fb_conn->connector;
+
+		if (!enabled[i])
+			continue;
+
+		if (connector->force != DRM_FORCE_UNSPECIFIED)
+			return false;
+	}
+
+	save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool),
+			       GFP_KERNEL);
+	if (!save_enabled)
+		return false;
+
+	memcpy(save_enabled, enabled, dev->mode_config.num_connector);
+
+	for (i = 0; i < fb_helper->connector_count; i++) {
+		struct drm_fb_helper_connector *fb_conn;
+		struct drm_connector *connector;
+		struct drm_encoder *encoder;
+		struct drm_fb_helper_crtc *new_crtc;
+
+		fb_conn = fb_helper->connector_info[i];
+		connector = fb_conn->connector;
+
+		if (connector->status == connector_status_connected)
+			num_connectors_detected++;
+
+		if (!enabled[i]) {
+			DRM_DEBUG_KMS("connector %d not enabled, skipping\n",
+				      connector->base.id);
+			continue;
+		}
+
+		encoder = connector->encoder;
+		if (!encoder || WARN_ON(!encoder->crtc)) {
+			DRM_DEBUG_KMS("connector %d has no encoder or crtc, skipping\n",
+				      connector->base.id);
+			enabled[i] = false;
+			continue;
+		}
+
+		num_connectors_enabled++;
+
+		new_crtc = intel_fb_helper_crtc(fb_helper, encoder->crtc);
+
+		/*
+		 * Make sure we're not trying to drive multiple connectors
+		 * with a single CRTC, since our cloning support may not
+		 * match the BIOS.
+		 */
+		for (j = 0; j < fb_helper->connector_count; j++) {
+			if (crtcs[j] == new_crtc) {
+				DRM_DEBUG_KMS("fallback: cloned configuration\n");
+				fallback = true;
+				goto out;
+			}
+		}
+
+		DRM_DEBUG_KMS("looking for cmdline mode on connector %d\n",
+			      fb_conn->connector->base.id);
+
+		/* go for command line mode first */
+		modes[i] = drm_pick_cmdline_mode(fb_conn, width, height);
+
+		/* try for preferred next */
+		if (!modes[i]) {
+			DRM_DEBUG_KMS("looking for preferred mode on connector %d\n",
+				      fb_conn->connector->base.id);
+			modes[i] = drm_has_preferred_mode(fb_conn, width,
+							  height);
+		}
+
+		/* last resort: use current mode */
+		if (!modes[i]) {
+			/*
+			 * IMPORTANT: We want to use the adjusted mode (i.e.
+			 * after the panel fitter upscaling) as the initial
+			 * config, not the input mode, which is what crtc->mode
+			 * usually contains. But since our current fastboot
+			 * code puts a mode derived from the post-pfit timings
+			 * into crtc->mode this works out correctly. We don't
+			 * use hwmode anywhere right now, so use it for this
+			 * since the fb helper layer wants a pointer to
+			 * something we own.
+			 */
+			intel_mode_from_pipe_config(&encoder->crtc->hwmode,
+						    &to_intel_crtc(encoder->crtc)->config);
+			modes[i] = &encoder->crtc->hwmode;
+		}
+		crtcs[i] = new_crtc;
+
+		DRM_DEBUG_KMS("connector %s on crtc %d: %s\n",
+			      drm_get_connector_name(connector),
+			      encoder->crtc->base.id,
+			      modes[i]->name);
+
+		fallback = false;
+	}
+
+	/*
+	 * If the BIOS didn't enable everything it could, fall back to have the
+	 * same user experiencing of lighting up as much as possible like the
+	 * fbdev helper library.
+	 */
+	if (num_connectors_enabled != num_connectors_detected &&
+	    num_connectors_enabled < INTEL_INFO(dev)->num_pipes) {
+		DRM_DEBUG_KMS("fallback: Not all outputs enabled\n");
+		DRM_DEBUG_KMS("Enabled: %i, detected: %i\n", num_connectors_enabled,
+			      num_connectors_detected);
+		fallback = true;
+	}
+
+out:
+	if (fallback) {
+		DRM_DEBUG_KMS("Not using firmware configuration\n");
+		memcpy(enabled, save_enabled, dev->mode_config.num_connector);
+		kfree(save_enabled);
+		return false;
+	}
+
+	kfree(save_enabled);
+	return true;
+}
+
 static struct drm_fb_helper_funcs intel_fb_helper_funcs = {
+	.initial_config = intel_fb_initial_config,
 	.gamma_set = intel_crtc_fb_gamma_set,
 	.gamma_get = intel_crtc_fb_gamma_get,
 	.fb_probe = intelfb_create,
@@ -258,8 +450,8 @@
 
 	drm_fb_helper_fini(&ifbdev->helper);
 
-	drm_framebuffer_unregister_private(&ifbdev->ifb.base);
-	intel_framebuffer_fini(&ifbdev->ifb);
+	drm_framebuffer_unregister_private(&ifbdev->fb->base);
+	drm_framebuffer_remove(&ifbdev->fb->base);
 }
 
 int intel_fbdev_init(struct drm_device *dev)
@@ -322,7 +514,7 @@
 	 * been restored from swap. If the object is stolen however, it will be
 	 * full of whatever garbage was left in there.
 	 */
-	if (state == FBINFO_STATE_RUNNING && ifbdev->ifb.obj->stolen)
+	if (state == FBINFO_STATE_RUNNING && ifbdev->fb->obj->stolen)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	fb_set_suspend(info, state);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 43872f0..ceb4797 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -425,7 +425,7 @@
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	u32 reg = VIDEO_DIP_CTL;
 	u32 val = I915_READ(reg);
-	u32 port;
+	u32 port = VIDEO_DIP_PORT(intel_dig_port->port);
 
 	assert_hdmi_port_disabled(intel_hdmi);
 
@@ -449,18 +449,6 @@
 		return;
 	}
 
-	switch (intel_dig_port->port) {
-	case PORT_B:
-		port = VIDEO_DIP_PORT_B;
-		break;
-	case PORT_C:
-		port = VIDEO_DIP_PORT_C;
-		break;
-	default:
-		BUG();
-		return;
-	}
-
 	if (port != (val & VIDEO_DIP_PORT_MASK)) {
 		if (val & VIDEO_DIP_ENABLE) {
 			val &= ~VIDEO_DIP_ENABLE;
@@ -491,7 +479,7 @@
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	u32 reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
-	u32 port;
+	u32 port = VIDEO_DIP_PORT(intel_dig_port->port);
 
 	assert_hdmi_port_disabled(intel_hdmi);
 
@@ -507,21 +495,6 @@
 		return;
 	}
 
-	switch (intel_dig_port->port) {
-	case PORT_B:
-		port = VIDEO_DIP_PORT_B;
-		break;
-	case PORT_C:
-		port = VIDEO_DIP_PORT_C;
-		break;
-	case PORT_D:
-		port = VIDEO_DIP_PORT_D;
-		break;
-	default:
-		BUG();
-		return;
-	}
-
 	if (port != (val & VIDEO_DIP_PORT_MASK)) {
 		if (val & VIDEO_DIP_ENABLE) {
 			val &= ~VIDEO_DIP_ENABLE;
@@ -694,8 +667,13 @@
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	enum intel_display_power_domain power_domain;
 	u32 tmp;
 
+	power_domain = intel_display_port_power_domain(encoder);
+	if (!intel_display_power_enabled(dev_priv, power_domain))
+		return false;
+
 	tmp = I915_READ(intel_hdmi->hdmi_reg);
 
 	if (!(tmp & SDVO_ENABLE))
@@ -847,7 +825,7 @@
 {
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 
-	if (IS_G4X(dev))
+	if (!hdmi->has_hdmi_sink || IS_G4X(dev))
 		return 165000;
 	else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
 		return 300000;
@@ -901,8 +879,8 @@
 	 * outputs. We also need to check that the higher clock still fits
 	 * within limits.
 	 */
-	if (pipe_config->pipe_bpp > 8*3 && clock_12bpc <= portclock_limit
-	    && HAS_PCH_SPLIT(dev)) {
+	if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink &&
+	    clock_12bpc <= portclock_limit && HAS_PCH_SPLIT(dev)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
 
@@ -936,11 +914,15 @@
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct edid *edid;
+	enum intel_display_power_domain power_domain;
 	enum drm_connector_status status = connector_status_disconnected;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, drm_get_connector_name(connector));
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	intel_hdmi->has_hdmi_sink = false;
 	intel_hdmi->has_audio = false;
 	intel_hdmi->rgb_quant_range_selectable = false;
@@ -968,31 +950,48 @@
 		intel_encoder->type = INTEL_OUTPUT_HDMI;
 	}
 
+	intel_display_power_put(dev_priv, power_domain);
+
 	return status;
 }
 
 static int intel_hdmi_get_modes(struct drm_connector *connector)
 {
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_encoder *intel_encoder = intel_attached_encoder(connector);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	enum intel_display_power_domain power_domain;
+	int ret;
 
 	/* We should parse the EDID data and find out if it's an HDMI sink so
 	 * we can send audio to it.
 	 */
 
-	return intel_ddc_get_modes(connector,
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
+	ret = intel_ddc_get_modes(connector,
 				   intel_gmbus_get_adapter(dev_priv,
 							   intel_hdmi->ddc_bus));
+
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static bool
 intel_hdmi_detect_audio(struct drm_connector *connector)
 {
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_encoder *intel_encoder = intel_attached_encoder(connector);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	struct edid *edid;
 	bool has_audio = false;
 
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
 	edid = drm_get_edid(connector,
 			    intel_gmbus_get_adapter(dev_priv,
 						    intel_hdmi->ddc_bus));
@@ -1002,6 +1001,8 @@
 		kfree(edid);
 	}
 
+	intel_display_power_put(dev_priv, power_domain);
+
 	return has_audio;
 }
 
@@ -1263,6 +1264,7 @@
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	intel_hdmi_add_properties(intel_hdmi, connector);
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 3f3043b..fecff3c 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -899,6 +899,7 @@
 	struct drm_encoder *encoder;
 	struct drm_display_mode *scan; /* *modes, *bios_mode; */
 	struct drm_display_mode *fixed_mode = NULL;
+	struct drm_display_mode *downclock_mode = NULL;
 	struct edid *edid;
 	struct drm_crtc *crtc;
 	u32 lvds;
@@ -957,6 +958,7 @@
 	intel_encoder->get_hw_state = intel_lvds_get_hw_state;
 	intel_encoder->get_config = intel_lvds_get_config;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_LVDS;
@@ -1032,15 +1034,14 @@
 
 			fixed_mode = drm_mode_duplicate(dev, scan);
 			if (fixed_mode) {
-				intel_connector->panel.downclock_mode =
+				downclock_mode =
 					intel_find_panel_downclock(dev,
 					fixed_mode, connector);
-				if (intel_connector->panel.downclock_mode !=
-					NULL &&	i915.lvds_downclock) {
+				if (downclock_mode != NULL &&
+					i915.lvds_downclock) {
 					/* We found the downclock for LVDS. */
 					dev_priv->lvds_downclock_avail = true;
 					dev_priv->lvds_downclock =
-						intel_connector->panel.
 						downclock_mode->clock;
 					DRM_DEBUG_KMS("LVDS downclock is found"
 					" in EDID. Normal clock %dKhz, "
@@ -1116,7 +1117,7 @@
 	}
 	drm_sysfs_connector_add(connector);
 
-	intel_panel_init(&intel_connector->panel, fixed_mode);
+	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
 	intel_panel_setup_backlight(connector);
 
 	return;
@@ -1125,8 +1126,6 @@
 	DRM_DEBUG_KMS("No LVDS modes found, disabling.\n");
 	drm_connector_cleanup(connector);
 	drm_encoder_cleanup(encoder);
-	if (fixed_mode)
-		drm_mode_destroy(dev, fixed_mode);
 	kfree(lvds_encoder);
 	kfree(lvds_connector);
 	return;
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 424f094..312961a 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1076,7 +1076,7 @@
 	mutex_lock(&dev->struct_mutex);
 
 	if (new_bo->tiling_mode) {
-		DRM_ERROR("buffer used for overlay image can not be tiled\n");
+		DRM_DEBUG_KMS("buffer used for overlay image can not be tiled\n");
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -1349,7 +1349,7 @@
 		}
 		overlay->flip_addr = reg_bo->phys_obj->handle->busaddr;
 	} else {
-		ret = i915_gem_obj_ggtt_pin(reg_bo, PAGE_SIZE, true, false);
+		ret = i915_gem_obj_ggtt_pin(reg_bo, PAGE_SIZE, PIN_MAPPABLE);
 		if (ret) {
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index f1ee2c4..cb05840 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -689,7 +689,7 @@
 		freq /= 0xff;
 
 	ctl = freq << 17;
-	if (IS_GEN2(dev) && panel->backlight.combination_mode)
+	if (panel->backlight.combination_mode)
 		ctl |= BLM_LEGACY_MODE;
 	if (IS_PINEVIEW(dev) && panel->backlight.active_low_pwm)
 		ctl |= BLM_POLARITY_PNV;
@@ -970,7 +970,7 @@
 
 	ctl = I915_READ(BLC_PWM_CTL);
 
-	if (IS_GEN2(dev))
+	if (IS_GEN2(dev) || IS_I915GM(dev) || IS_I945GM(dev))
 		panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE;
 
 	if (IS_PINEVIEW(dev))
@@ -1190,9 +1190,11 @@
 }
 
 int intel_panel_init(struct intel_panel *panel,
-		     struct drm_display_mode *fixed_mode)
+		     struct drm_display_mode *fixed_mode,
+		     struct drm_display_mode *downclock_mode)
 {
 	panel->fixed_mode = fixed_mode;
+	panel->downclock_mode = downclock_mode;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f74d7f5..ad58ce3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -294,11 +294,14 @@
 
 	if (IS_IVYBRIDGE(dev)) {
 		/* WaFbcAsynchFlipDisableFbcQueue:ivb */
-		I915_WRITE(ILK_DISPLAY_CHICKEN1, ILK_FBCQ_DIS);
+		I915_WRITE(ILK_DISPLAY_CHICKEN1,
+			   I915_READ(ILK_DISPLAY_CHICKEN1) |
+			   ILK_FBCQ_DIS);
 	} else {
-		/* WaFbcAsynchFlipDisableFbcQueue:hsw */
-		I915_WRITE(HSW_PIPE_SLICE_CHICKEN_1(intel_crtc->pipe),
-			   HSW_BYPASS_FBC_QUEUE);
+		/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
+		I915_WRITE(CHICKEN_PIPESL_1(intel_crtc->pipe),
+			   I915_READ(CHICKEN_PIPESL_1(intel_crtc->pipe)) |
+			   HSW_FBCQ_DIS);
 	}
 
 	I915_WRITE(SNB_DPFC_CTL_SA,
@@ -540,7 +543,7 @@
 			DRM_DEBUG_KMS("mode too large for compression, disabling\n");
 		goto out_disable;
 	}
-	if ((INTEL_INFO(dev)->gen < 4 || IS_HASWELL(dev)) &&
+	if ((INTEL_INFO(dev)->gen < 4 || HAS_DDI(dev)) &&
 	    intel_crtc->plane != PLANE_A) {
 		if (set_no_fbc_reason(dev_priv, FBC_BAD_PLANE))
 			DRM_DEBUG_KMS("plane not A, disabling compression\n");
@@ -1131,7 +1134,7 @@
 		*plane_wm = display->max_wm;
 
 	/* Use the large buffer method to calculate cursor watermark */
-	line_time_us = ((htotal * 1000) / clock);
+	line_time_us = max(htotal * 1000 / clock, 1);
 	line_count = (cursor_latency_ns / line_time_us + 1000) / 1000;
 	entries = line_count * 64 * pixel_size;
 	tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8;
@@ -1207,7 +1210,7 @@
 	hdisplay = to_intel_crtc(crtc)->config.pipe_src_w;
 	pixel_size = crtc->fb->bits_per_pixel / 8;
 
-	line_time_us = (htotal * 1000) / clock;
+	line_time_us = max(htotal * 1000 / clock, 1);
 	line_count = (latency_ns / line_time_us + 1000) / 1000;
 	line_size = hdisplay * pixel_size;
 
@@ -1440,7 +1443,7 @@
 		unsigned long line_time_us;
 		int entries;
 
-		line_time_us = ((htotal * 1000) / clock);
+		line_time_us = max(htotal * 1000 / clock, 1);
 
 		/* Use ns/us then divide to preserve precision */
 		entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) *
@@ -1566,7 +1569,7 @@
 		unsigned long line_time_us;
 		int entries;
 
-		line_time_us = (htotal * 1000) / clock;
+		line_time_us = max(htotal * 1000 / clock, 1);
 
 		/* Use ns/us then divide to preserve precision */
 		entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) *
@@ -2741,7 +2744,7 @@
 		return NULL;
 	}
 
-	ret = i915_gem_obj_ggtt_pin(ctx, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0);
 	if (ret) {
 		DRM_ERROR("failed to pin power context: %d\n", ret);
 		goto err_unref;
@@ -3196,16 +3199,10 @@
 
 static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
 {
-	if (IS_GEN6(dev))
-		DRM_DEBUG_DRIVER("Sandybridge: deep RC6 disabled\n");
-
-	if (IS_HASWELL(dev))
-		DRM_DEBUG_DRIVER("Haswell: only RC6 available\n");
-
 	DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n",
-			(mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
-			(mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
-			(mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
+		 (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
+		 (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
+		 (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
 }
 
 int intel_enable_rc6(const struct drm_device *dev)
@@ -3222,14 +3219,10 @@
 	if (INTEL_INFO(dev)->gen == 5)
 		return 0;
 
-	if (IS_HASWELL(dev))
-		return INTEL_RC6_ENABLE;
+	if (IS_IVYBRIDGE(dev))
+		return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 
-	/* snb/ivb have more than one rc6 state. */
-	if (INTEL_INFO(dev)->gen == 6)
-		return INTEL_RC6_ENABLE;
-
-	return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
+	return INTEL_RC6_ENABLE;
 }
 
 static void gen6_enable_rps_interrupts(struct drm_device *dev)
@@ -3286,10 +3279,10 @@
 	/* 3: Enable RC6 */
 	if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
 		rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
-	DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off");
+	intel_print_rc6_info(dev, rc6_mask);
 	I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
-			GEN6_RC_CTL_EI_MODE(1) |
-			rc6_mask);
+				    GEN6_RC_CTL_EI_MODE(1) |
+				    rc6_mask);
 
 	/* 4 Program defaults and thresholds for RPS*/
 	I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(10)); /* Request 500 MHz */
@@ -3564,6 +3557,8 @@
 	u32 pcbr;
 	int pctx_size = 24*1024;
 
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
 	pcbr = I915_READ(VLV_PCBR);
 	if (pcbr) {
 		/* BIOS set it up already, grab the pre-alloc'd space */
@@ -3613,8 +3608,6 @@
 		I915_WRITE(GTFIFODBG, gtfifodbg);
 	}
 
-	valleyview_setup_pctx(dev);
-
 	/* If VLV, Forcewake all wells, else re-direct to regular path */
 	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
@@ -3903,9 +3896,10 @@
 
 unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
 	unsigned long val;
 
-	if (dev_priv->info->gen != 5)
+	if (INTEL_INFO(dev)->gen != 5)
 		return 0;
 
 	spin_lock_irq(&mchdev_lock);
@@ -3934,6 +3928,7 @@
 
 static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
 {
+	struct drm_device *dev = dev_priv->dev;
 	static const struct v_table {
 		u16 vd; /* in .1 mil */
 		u16 vm; /* in .1 mil */
@@ -4067,7 +4062,7 @@
 		{ 16000, 14875, },
 		{ 16125, 15000, },
 	};
-	if (dev_priv->info->is_mobile)
+	if (INTEL_INFO(dev)->is_mobile)
 		return v_table[pxvid].vm;
 	else
 		return v_table[pxvid].vd;
@@ -4110,7 +4105,9 @@
 
 void i915_update_gfx_val(struct drm_i915_private *dev_priv)
 {
-	if (dev_priv->info->gen != 5)
+	struct drm_device *dev = dev_priv->dev;
+
+	if (INTEL_INFO(dev)->gen != 5)
 		return;
 
 	spin_lock_irq(&mchdev_lock);
@@ -4159,9 +4156,10 @@
 
 unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
 	unsigned long val;
 
-	if (dev_priv->info->gen != 5)
+	if (INTEL_INFO(dev)->gen != 5)
 		return 0;
 
 	spin_lock_irq(&mchdev_lock);
@@ -4476,6 +4474,8 @@
 		ironlake_enable_rc6(dev);
 		intel_init_emon(dev);
 	} else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+		if (IS_VALLEYVIEW(dev))
+			valleyview_setup_pctx(dev);
 		/*
 		 * PCU communication is slow and this doesn't need to be
 		 * done at any specific time, so do this out of our fast path
@@ -4666,6 +4666,17 @@
 		I915_WRITE(GEN6_GT_MODE,
 			   _MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE));
 
+	/*
+	 * BSpec recoomends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	I915_WRITE(GEN6_GT_MODE,
+		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
 	ilk_init_lp_watermarks(dev);
 
 	I915_WRITE(CACHE_MODE_0,
@@ -4693,9 +4704,17 @@
 		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
 		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
 
-	/* Bspec says we need to always set all mask bits. */
-	I915_WRITE(_3D_CHICKEN3, (0xFFFF << 16) |
-		   _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL);
+	/* WaStripsFansDisableFastClipPerformanceFix:snb */
+	I915_WRITE(_3D_CHICKEN3,
+		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
+
+	/*
+	 * Bspec says:
+	 * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
+	 * 3DSTATE_SF number of SF output attributes is more than 16."
+	 */
+	I915_WRITE(_3D_CHICKEN3,
+		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
 
 	/*
 	 * According to the spec the following bits should be
@@ -4721,11 +4740,6 @@
 
 	g4x_disable_trickle_feed(dev);
 
-	/* The default value should be 0x200 according to docs, but the two
-	 * platforms I checked have a 0 for this. (Maybe BIOS overrides?) */
-	I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_DISABLE(0xffff));
-	I915_WRITE(GEN6_GT_MODE, _MASKED_BIT_ENABLE(GEN6_GT_MODE_HI));
-
 	cpt_init_clock_gating(dev);
 
 	gen6_check_mch_setup(dev);
@@ -4783,7 +4797,7 @@
 static void gen8_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum pipe i;
+	enum pipe pipe;
 
 	I915_WRITE(WM3_LP_ILK, 0);
 	I915_WRITE(WM2_LP_ILK, 0);
@@ -4792,6 +4806,15 @@
 	/* FIXME(BDW): Check all the w/a, some might only apply to
 	 * pre-production hw. */
 
+	/* WaDisablePartialInstShootdown:bdw */
+	I915_WRITE(GEN8_ROW_CHICKEN,
+		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
+
+	/* WaDisableThreadStallDopClockGating:bdw */
+	/* FIXME: Unclear whether we really need this on production bdw. */
+	I915_WRITE(GEN8_ROW_CHICKEN,
+		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+
 	/*
 	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
 	 * pre-production hardware
@@ -4819,10 +4842,10 @@
 		   I915_READ(CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
 	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
-	for_each_pipe(i) {
-		I915_WRITE(CHICKEN_PIPESL_1(i),
-			   I915_READ(CHICKEN_PIPESL_1(i) |
-				     DPRS_MASK_VBLANK_SRD));
+	for_each_pipe(pipe) {
+		I915_WRITE(CHICKEN_PIPESL_1(pipe),
+			   I915_READ(CHICKEN_PIPESL_1(pipe)) |
+			   BDW_DPRS_MASK_VBLANK_SRD);
 	}
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
@@ -4838,6 +4861,24 @@
 	I915_WRITE(GEN7_FF_THREAD_MODE,
 		   I915_READ(GEN7_FF_THREAD_MODE) &
 		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	I915_WRITE(GEN7_GT_MODE,
+		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
+	I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL,
+		   _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
+
+	/* WaDisableSDEUnitClockGating:bdw */
+	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 }
 
 static void haswell_init_clock_gating(struct drm_device *dev)
@@ -4868,6 +4909,17 @@
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
 
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	I915_WRITE(GEN7_GT_MODE,
+		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -4941,14 +4993,27 @@
 
 	gen7_setup_fixed_func_scheduler(dev_priv);
 
-	/* enable HiZ Raw Stall Optimization */
-	I915_WRITE(CACHE_MODE_0_GEN7,
-		   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+	if (0) { /* causes HiZ corruption on ivb:gt1 */
+		/* enable HiZ Raw Stall Optimization */
+		I915_WRITE(CACHE_MODE_0_GEN7,
+			   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+	}
 
 	/* WaDisable4x2SubspanOptimization:ivb */
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
 
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	I915_WRITE(GEN7_GT_MODE,
+		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 	snpcr &= ~GEN6_MBC_SNPCR_MASK;
 	snpcr |= GEN6_MBC_SNPCR_MED;
@@ -5001,9 +5066,6 @@
 		   _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
 				      GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
 
-	/* WaDisableL3CacheAging:vlv */
-	I915_WRITE(GEN7_L3CNTLREG1, I915_READ(GEN7_L3CNTLREG1) | GEN7_L3AGDIS);
-
 	/* WaForceL3Serialization:vlv */
 	I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
 		   ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
@@ -5164,19 +5226,16 @@
  * enable it, so check if it's enabled and also check if we've requested it to
  * be enabled.
  */
-static bool hsw_power_well_enabled(struct drm_device *dev,
+static bool hsw_power_well_enabled(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	return I915_READ(HSW_PWR_WELL_DRIVER) ==
 		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
 }
 
-bool intel_display_power_enabled_sw(struct drm_device *dev,
+bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv,
 				    enum intel_display_power_domain domain)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
 
 	power_domains = &dev_priv->power_domains;
@@ -5184,10 +5243,9 @@
 	return power_domains->domain_use_count[domain];
 }
 
-bool intel_display_power_enabled(struct drm_device *dev,
+bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
 				 enum intel_display_power_domain domain)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
 	struct i915_power_well *power_well;
 	bool is_enabled;
@@ -5202,7 +5260,7 @@
 		if (power_well->always_on)
 			continue;
 
-		if (!power_well->is_enabled(dev, power_well)) {
+		if (!power_well->ops->is_enabled(dev_priv, power_well)) {
 			is_enabled = false;
 			break;
 		}
@@ -5212,6 +5270,12 @@
 	return is_enabled;
 }
 
+/*
+ * Starting with Haswell, we have a "Power Down Well" that can be turned off
+ * when not needed anymore. We have 4 registers that can request the power well
+ * to be enabled, and it will only be disabled if none of the registers is
+ * requesting it to be enabled.
+ */
 static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -5248,10 +5312,17 @@
 	}
 }
 
+static void reset_vblank_counter(struct drm_device *dev, enum pipe pipe)
+{
+	assert_spin_locked(&dev->vbl_lock);
+
+	dev->vblank[pipe].last = 0;
+}
+
 static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
-	enum pipe p;
+	enum pipe pipe;
 	unsigned long irqflags;
 
 	/*
@@ -5262,16 +5333,15 @@
 	 * FIXME: Should we do this in general in drm_vblank_post_modeset?
 	 */
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
-	for_each_pipe(p)
-		if (p != PIPE_A)
-			dev->vblank[p].last = 0;
+	for_each_pipe(pipe)
+		if (pipe != PIPE_A)
+			reset_vblank_counter(dev, pipe);
 	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 }
 
-static void hsw_set_power_well(struct drm_device *dev,
+static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 			       struct i915_power_well *power_well, bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool is_enabled, enable_requested;
 	uint32_t tmp;
 
@@ -5305,35 +5375,204 @@
 	}
 }
 
-static void __intel_power_well_get(struct drm_device *dev,
+static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	hsw_set_power_well(dev_priv, power_well, power_well->count > 0);
 
-	if (!power_well->count++ && power_well->set) {
-		hsw_disable_package_c8(dev_priv);
-		power_well->set(dev, power_well, true);
-	}
+	/*
+	 * We're taking over the BIOS, so clear any requests made by it since
+	 * the driver is in charge now.
+	 */
+	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST)
+		I915_WRITE(HSW_PWR_WELL_BIOS, 0);
 }
 
-static void __intel_power_well_put(struct drm_device *dev,
+static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
+				  struct i915_power_well *power_well)
+{
+	hsw_disable_package_c8(dev_priv);
+	hsw_set_power_well(dev_priv, power_well, true);
+}
+
+static void hsw_power_well_disable(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	WARN_ON(!power_well->count);
-
-	if (!--power_well->count && power_well->set &&
-	    i915.disable_power_well) {
-		power_well->set(dev, power_well, false);
-		hsw_enable_package_c8(dev_priv);
-	}
+	hsw_set_power_well(dev_priv, power_well, false);
+	hsw_enable_package_c8(dev_priv);
 }
 
-void intel_display_power_get(struct drm_device *dev,
+static void i9xx_always_on_power_well_noop(struct drm_i915_private *dev_priv,
+					   struct i915_power_well *power_well)
+{
+}
+
+static bool i9xx_always_on_power_well_enabled(struct drm_i915_private *dev_priv,
+					     struct i915_power_well *power_well)
+{
+	return true;
+}
+
+static void vlv_set_power_well(struct drm_i915_private *dev_priv,
+			       struct i915_power_well *power_well, bool enable)
+{
+	enum punit_power_well power_well_id = power_well->data;
+	u32 mask;
+	u32 state;
+	u32 ctrl;
+
+	mask = PUNIT_PWRGT_MASK(power_well_id);
+	state = enable ? PUNIT_PWRGT_PWR_ON(power_well_id) :
+			 PUNIT_PWRGT_PWR_GATE(power_well_id);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+#define COND \
+	((vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS) & mask) == state)
+
+	if (COND)
+		goto out;
+
+	ctrl = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_CTRL);
+	ctrl &= ~mask;
+	ctrl |= state;
+	vlv_punit_write(dev_priv, PUNIT_REG_PWRGT_CTRL, ctrl);
+
+	if (wait_for(COND, 100))
+		DRM_ERROR("timout setting power well state %08x (%08x)\n",
+			  state,
+			  vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_CTRL));
+
+#undef COND
+
+out:
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void vlv_power_well_sync_hw(struct drm_i915_private *dev_priv,
+				   struct i915_power_well *power_well)
+{
+	vlv_set_power_well(dev_priv, power_well, power_well->count > 0);
+}
+
+static void vlv_power_well_enable(struct drm_i915_private *dev_priv,
+				  struct i915_power_well *power_well)
+{
+	vlv_set_power_well(dev_priv, power_well, true);
+}
+
+static void vlv_power_well_disable(struct drm_i915_private *dev_priv,
+				   struct i915_power_well *power_well)
+{
+	vlv_set_power_well(dev_priv, power_well, false);
+}
+
+static bool vlv_power_well_enabled(struct drm_i915_private *dev_priv,
+				   struct i915_power_well *power_well)
+{
+	int power_well_id = power_well->data;
+	bool enabled = false;
+	u32 mask;
+	u32 state;
+	u32 ctrl;
+
+	mask = PUNIT_PWRGT_MASK(power_well_id);
+	ctrl = PUNIT_PWRGT_PWR_ON(power_well_id);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	state = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS) & mask;
+	/*
+	 * We only ever set the power-on and power-gate states, anything
+	 * else is unexpected.
+	 */
+	WARN_ON(state != PUNIT_PWRGT_PWR_ON(power_well_id) &&
+		state != PUNIT_PWRGT_PWR_GATE(power_well_id));
+	if (state == ctrl)
+		enabled = true;
+
+	/*
+	 * A transient state at this point would mean some unexpected party
+	 * is poking at the power controls too.
+	 */
+	ctrl = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_CTRL) & mask;
+	WARN_ON(ctrl != state);
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	return enabled;
+}
+
+static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv,
+					  struct i915_power_well *power_well)
+{
+	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D);
+
+	vlv_set_power_well(dev_priv, power_well, true);
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	valleyview_enable_display_irqs(dev_priv);
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	/*
+	 * During driver initialization we need to defer enabling hotplug
+	 * processing until fbdev is set up.
+	 */
+	if (dev_priv->enable_hotplug_processing)
+		intel_hpd_init(dev_priv->dev);
+
+	i915_redisable_vga_power_on(dev_priv->dev);
+}
+
+static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv,
+					   struct i915_power_well *power_well)
+{
+	struct drm_device *dev = dev_priv->dev;
+	enum pipe pipe;
+
+	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D);
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	for_each_pipe(pipe)
+		__intel_set_cpu_fifo_underrun_reporting(dev, pipe, false);
+
+	valleyview_disable_display_irqs(dev_priv);
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	spin_lock_irq(&dev->vbl_lock);
+	for_each_pipe(pipe)
+		reset_vblank_counter(dev, pipe);
+	spin_unlock_irq(&dev->vbl_lock);
+
+	vlv_set_power_well(dev_priv, power_well, false);
+}
+
+static void check_power_well_state(struct drm_i915_private *dev_priv,
+				   struct i915_power_well *power_well)
+{
+	bool enabled = power_well->ops->is_enabled(dev_priv, power_well);
+
+	if (power_well->always_on || !i915.disable_power_well) {
+		if (!enabled)
+			goto mismatch;
+
+		return;
+	}
+
+	if (enabled != (power_well->count > 0))
+		goto mismatch;
+
+	return;
+
+mismatch:
+	WARN(1, "state mismatch for '%s' (always_on %d hw state %d use-count %d disable_power_well %d\n",
+		  power_well->name, power_well->always_on, enabled,
+		  power_well->count, i915.disable_power_well);
+}
+
+void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
 	struct i915_power_well *power_well;
 	int i;
@@ -5342,18 +5581,23 @@
 
 	mutex_lock(&power_domains->lock);
 
-	for_each_power_well(i, power_well, BIT(domain), power_domains)
-		__intel_power_well_get(dev, power_well);
+	for_each_power_well(i, power_well, BIT(domain), power_domains) {
+		if (!power_well->count++) {
+			DRM_DEBUG_KMS("enabling %s\n", power_well->name);
+			power_well->ops->enable(dev_priv, power_well);
+		}
+
+		check_power_well_state(dev_priv, power_well);
+	}
 
 	power_domains->domain_use_count[domain]++;
 
 	mutex_unlock(&power_domains->lock);
 }
 
-void intel_display_power_put(struct drm_device *dev,
+void intel_display_power_put(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
 	struct i915_power_well *power_well;
 	int i;
@@ -5365,8 +5609,16 @@
 	WARN_ON(!power_domains->domain_use_count[domain]);
 	power_domains->domain_use_count[domain]--;
 
-	for_each_power_well_rev(i, power_well, BIT(domain), power_domains)
-		__intel_power_well_put(dev, power_well);
+	for_each_power_well_rev(i, power_well, BIT(domain), power_domains) {
+		WARN_ON(!power_well->count);
+
+		if (!--power_well->count && i915.disable_power_well) {
+			DRM_DEBUG_KMS("disabling %s\n", power_well->name);
+			power_well->ops->disable(dev_priv, power_well);
+		}
+
+		check_power_well_state(dev_priv, power_well);
+	}
 
 	mutex_unlock(&power_domains->lock);
 }
@@ -5383,7 +5635,7 @@
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
-	intel_display_power_get(dev_priv->dev, POWER_DOMAIN_AUDIO);
+	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
 }
 EXPORT_SYMBOL_GPL(i915_request_power_well);
 
@@ -5397,29 +5649,99 @@
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
-	intel_display_power_put(dev_priv->dev, POWER_DOMAIN_AUDIO);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
 }
 EXPORT_SYMBOL_GPL(i915_release_power_well);
 
+#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1)
+
+#define HSW_ALWAYS_ON_POWER_DOMAINS (			\
+	BIT(POWER_DOMAIN_PIPE_A) |			\
+	BIT(POWER_DOMAIN_TRANSCODER_EDP) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_A_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_A_4_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_CRT) |			\
+	BIT(POWER_DOMAIN_INIT))
+#define HSW_DISPLAY_POWER_DOMAINS (				\
+	(POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define BDW_ALWAYS_ON_POWER_DOMAINS (			\
+	HSW_ALWAYS_ON_POWER_DOMAINS |			\
+	BIT(POWER_DOMAIN_PIPE_A_PANEL_FITTER))
+#define BDW_DISPLAY_POWER_DOMAINS (				\
+	(POWER_DOMAIN_MASK & ~BDW_ALWAYS_ON_POWER_DOMAINS) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define VLV_ALWAYS_ON_POWER_DOMAINS	BIT(POWER_DOMAIN_INIT)
+#define VLV_DISPLAY_POWER_DOMAINS	POWER_DOMAIN_MASK
+
+#define VLV_DPIO_CMN_BC_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_CRT) |		\
+	BIT(POWER_DOMAIN_INIT))
+
+#define VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
+	.sync_hw = i9xx_always_on_power_well_noop,
+	.enable = i9xx_always_on_power_well_noop,
+	.disable = i9xx_always_on_power_well_noop,
+	.is_enabled = i9xx_always_on_power_well_enabled,
+};
+
 static struct i915_power_well i9xx_always_on_power_well[] = {
 	{
 		.name = "always-on",
 		.always_on = 1,
 		.domains = POWER_DOMAIN_MASK,
+		.ops = &i9xx_always_on_power_well_ops,
 	},
 };
 
+static const struct i915_power_well_ops hsw_power_well_ops = {
+	.sync_hw = hsw_power_well_sync_hw,
+	.enable = hsw_power_well_enable,
+	.disable = hsw_power_well_disable,
+	.is_enabled = hsw_power_well_enabled,
+};
+
 static struct i915_power_well hsw_power_wells[] = {
 	{
 		.name = "always-on",
 		.always_on = 1,
 		.domains = HSW_ALWAYS_ON_POWER_DOMAINS,
+		.ops = &i9xx_always_on_power_well_ops,
 	},
 	{
 		.name = "display",
-		.domains = POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS,
-		.is_enabled = hsw_power_well_enabled,
-		.set = hsw_set_power_well,
+		.domains = HSW_DISPLAY_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
 	},
 };
 
@@ -5428,12 +5750,83 @@
 		.name = "always-on",
 		.always_on = 1,
 		.domains = BDW_ALWAYS_ON_POWER_DOMAINS,
+		.ops = &i9xx_always_on_power_well_ops,
 	},
 	{
 		.name = "display",
-		.domains = POWER_DOMAIN_MASK & ~BDW_ALWAYS_ON_POWER_DOMAINS,
-		.is_enabled = hsw_power_well_enabled,
-		.set = hsw_set_power_well,
+		.domains = BDW_DISPLAY_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+	},
+};
+
+static const struct i915_power_well_ops vlv_display_power_well_ops = {
+	.sync_hw = vlv_power_well_sync_hw,
+	.enable = vlv_display_power_well_enable,
+	.disable = vlv_display_power_well_disable,
+	.is_enabled = vlv_power_well_enabled,
+};
+
+static const struct i915_power_well_ops vlv_dpio_power_well_ops = {
+	.sync_hw = vlv_power_well_sync_hw,
+	.enable = vlv_power_well_enable,
+	.disable = vlv_power_well_disable,
+	.is_enabled = vlv_power_well_enabled,
+};
+
+static struct i915_power_well vlv_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = VLV_ALWAYS_ON_POWER_DOMAINS,
+		.ops = &i9xx_always_on_power_well_ops,
+	},
+	{
+		.name = "display",
+		.domains = VLV_DISPLAY_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DISP2D,
+		.ops = &vlv_display_power_well_ops,
+	},
+	{
+		.name = "dpio-common",
+		.domains = VLV_DPIO_CMN_BC_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DPIO_CMN_BC,
+		.ops = &vlv_dpio_power_well_ops,
+	},
+	{
+		.name = "dpio-tx-b-01",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_01,
+	},
+	{
+		.name = "dpio-tx-b-23",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_23,
+	},
+	{
+		.name = "dpio-tx-c-01",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_01,
+	},
+	{
+		.name = "dpio-tx-c-23",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_23,
 	},
 };
 
@@ -5442,9 +5835,8 @@
 	(power_domains)->power_well_count = ARRAY_SIZE(__power_wells);	\
 })
 
-int intel_power_domains_init(struct drm_device *dev)
+int intel_power_domains_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 
 	mutex_init(&power_domains->lock);
@@ -5453,12 +5845,14 @@
 	 * The enabling order will be from lower to higher indexed wells,
 	 * the disabling order is reversed.
 	 */
-	if (IS_HASWELL(dev)) {
+	if (IS_HASWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, hsw_power_wells);
 		hsw_pwr = power_domains;
-	} else if (IS_BROADWELL(dev)) {
+	} else if (IS_BROADWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, bdw_power_wells);
 		hsw_pwr = power_domains;
+	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
+		set_power_wells(power_domains, vlv_power_wells);
 	} else {
 		set_power_wells(power_domains, i9xx_always_on_power_well);
 	}
@@ -5466,47 +5860,28 @@
 	return 0;
 }
 
-void intel_power_domains_remove(struct drm_device *dev)
+void intel_power_domains_remove(struct drm_i915_private *dev_priv)
 {
 	hsw_pwr = NULL;
 }
 
-static void intel_power_domains_resume(struct drm_device *dev)
+static void intel_power_domains_resume(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 	struct i915_power_well *power_well;
 	int i;
 
 	mutex_lock(&power_domains->lock);
-	for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) {
-		if (power_well->set)
-			power_well->set(dev, power_well, power_well->count > 0);
-	}
+	for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains)
+		power_well->ops->sync_hw(dev_priv, power_well);
 	mutex_unlock(&power_domains->lock);
 }
 
-/*
- * Starting with Haswell, we have a "Power Down Well" that can be turned off
- * when not needed anymore. We have 4 registers that can request the power well
- * to be enabled, and it will only be disabled if none of the registers is
- * requesting it to be enabled.
- */
-void intel_power_domains_init_hw(struct drm_device *dev)
+void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/* For now, we need the power well to be always enabled. */
-	intel_display_set_init_power(dev, true);
-	intel_power_domains_resume(dev);
-
-	if (!(IS_HASWELL(dev) || IS_BROADWELL(dev)))
-		return;
-
-	/* We're taking over the BIOS, so clear any requests made by it since
-	 * the driver is in charge now. */
-	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST)
-		I915_WRITE(HSW_PWR_WELL_BIOS, 0);
+	intel_display_set_init_power(dev_priv, true);
+	intel_power_domains_resume(dev_priv);
 }
 
 /* Disables PC8 so we can use the GMBUS and DP AUX interrupts. */
@@ -5783,10 +6158,9 @@
 
 	mutex_init(&dev_priv->pc8.lock);
 	dev_priv->pc8.requirements_met = false;
-	dev_priv->pc8.gpu_idle = false;
 	dev_priv->pc8.irqs_disabled = false;
 	dev_priv->pc8.enabled = false;
-	dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
+	dev_priv->pc8.disable_count = 1; /* requirements_met */
 	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
 	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
 			  intel_gen6_powersave_work);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 8c1c0bc..8590921 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -531,9 +531,11 @@
 		goto err;
 	}
 
-	i915_gem_object_set_cache_level(ring->scratch.obj, I915_CACHE_LLC);
+	ret = i915_gem_object_set_cache_level(ring->scratch.obj, I915_CACHE_LLC);
+	if (ret)
+		goto err_unref;
 
-	ret = i915_gem_obj_ggtt_pin(ring->scratch.obj, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(ring->scratch.obj, 4096, 0);
 	if (ret)
 		goto err_unref;
 
@@ -569,7 +571,7 @@
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
 	 * programmed to '1' on all products.
 	 *
-	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
+	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw
 	 */
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
@@ -1271,12 +1273,13 @@
 		goto err;
 	}
 
-	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-
-	ret = i915_gem_obj_ggtt_pin(obj, 4096, true, false);
-	if (ret != 0) {
+	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
+	if (ret)
 		goto err_unref;
-	}
+
+	ret = i915_gem_obj_ggtt_pin(obj, 4096, 0);
+	if (ret)
+		goto err_unref;
 
 	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
@@ -1356,7 +1359,7 @@
 
 	ring->obj = obj;
 
-	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
 	if (ret)
 		goto err_unref;
 
@@ -1385,6 +1388,8 @@
 	if (IS_I830(ring->dev) || IS_845G(ring->dev))
 		ring->effective_size -= 128;
 
+	i915_cmd_parser_init_ring(ring);
+
 	return 0;
 
 err_unmap:
@@ -1513,7 +1518,8 @@
 			return 0;
 		}
 
-		if (dev->primary->master) {
+		if (!drm_core_check_feature(dev, DRIVER_MODESET) &&
+		    dev->primary->master) {
 			struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
 			if (master_priv->sarea_priv)
 				master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
@@ -1939,7 +1945,7 @@
 			return -ENOMEM;
 		}
 
-		ret = i915_gem_obj_ggtt_pin(obj, 0, true, false);
+		ret = i915_gem_obj_ggtt_pin(obj, 0, 0);
 		if (ret != 0) {
 			drm_gem_object_unreference(&obj->base);
 			DRM_ERROR("Failed to ping batch bo\n");
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 08b91c6..09af920 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -164,6 +164,38 @@
 		u32 gtt_offset;
 		volatile u32 *cpu_page;
 	} scratch;
+
+	/*
+	 * Tables of commands the command parser needs to know about
+	 * for this ring.
+	 */
+	const struct drm_i915_cmd_table *cmd_tables;
+	int cmd_table_count;
+
+	/*
+	 * Table of registers allowed in commands that read/write registers.
+	 */
+	const u32 *reg_table;
+	int reg_count;
+
+	/*
+	 * Table of registers allowed in commands that read/write registers, but
+	 * only from the DRM master.
+	 */
+	const u32 *master_reg_table;
+	int master_reg_count;
+
+	/*
+	 * Returns the bitmask for the length field of the specified command.
+	 * Return 0 for an unrecognized/invalid command.
+	 *
+	 * If the command parser finds an entry for a command in the ring's
+	 * cmd_tables, it gets the command's length based on the table entry.
+	 * If not, it calls this function to determine the per-ring length field
+	 * encoding for the command (i.e. certain opcode ranges use certain bits
+	 * to encode the command length in the header).
+	 */
+	u32 (*get_cmd_length_mask)(u32 cmd_header);
 };
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 95bdfb3..825853d 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2382,24 +2382,62 @@
 }
 
 static void
+intel_sdvo_connector_unregister(struct intel_connector *intel_connector)
+{
+	struct drm_connector *drm_connector;
+	struct intel_sdvo *sdvo_encoder;
+
+	drm_connector = &intel_connector->base;
+	sdvo_encoder = intel_attached_sdvo(&intel_connector->base);
+
+	sysfs_remove_link(&drm_connector->kdev->kobj,
+			  sdvo_encoder->ddc.dev.kobj.name);
+	intel_connector_unregister(intel_connector);
+}
+
+static int
 intel_sdvo_connector_init(struct intel_sdvo_connector *connector,
 			  struct intel_sdvo *encoder)
 {
-	drm_connector_init(encoder->base.base.dev,
-			   &connector->base.base,
+	struct drm_connector *drm_connector;
+	int ret;
+
+	drm_connector = &connector->base.base;
+	ret = drm_connector_init(encoder->base.base.dev,
+			   drm_connector,
 			   &intel_sdvo_connector_funcs,
 			   connector->base.base.connector_type);
+	if (ret < 0)
+		return ret;
 
-	drm_connector_helper_add(&connector->base.base,
+	drm_connector_helper_add(drm_connector,
 				 &intel_sdvo_connector_helper_funcs);
 
 	connector->base.base.interlace_allowed = 1;
 	connector->base.base.doublescan_allowed = 0;
 	connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB;
 	connector->base.get_hw_state = intel_sdvo_connector_get_hw_state;
+	connector->base.unregister = intel_sdvo_connector_unregister;
 
 	intel_connector_attach_encoder(&connector->base, &encoder->base);
-	drm_sysfs_connector_add(&connector->base.base);
+	ret = drm_sysfs_connector_add(drm_connector);
+	if (ret < 0)
+		goto err1;
+
+	ret = sysfs_create_link(&encoder->ddc.dev.kobj,
+				&drm_connector->kdev->kobj,
+				encoder->ddc.dev.kobj.name);
+	if (ret < 0)
+		goto err2;
+
+	return 0;
+
+err2:
+	drm_sysfs_connector_remove(drm_connector);
+err1:
+	drm_connector_cleanup(drm_connector);
+
+	return ret;
 }
 
 static void
@@ -2459,7 +2497,11 @@
 		intel_sdvo->is_hdmi = true;
 	}
 
-	intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo);
+	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
+		kfree(intel_sdvo_connector);
+		return false;
+	}
+
 	if (intel_sdvo->is_hdmi)
 		intel_sdvo_add_hdmi_properties(intel_sdvo, intel_sdvo_connector);
 
@@ -2490,7 +2532,10 @@
 
 	intel_sdvo->is_tv = true;
 
-	intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo);
+	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
+		kfree(intel_sdvo_connector);
+		return false;
+	}
 
 	if (!intel_sdvo_tv_create_property(intel_sdvo, intel_sdvo_connector, type))
 		goto err;
@@ -2534,8 +2579,11 @@
 		intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1;
 	}
 
-	intel_sdvo_connector_init(intel_sdvo_connector,
-				  intel_sdvo);
+	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
+		kfree(intel_sdvo_connector);
+		return false;
+	}
+
 	return true;
 }
 
@@ -2566,7 +2614,11 @@
 		intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1;
 	}
 
-	intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo);
+	if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
+		kfree(intel_sdvo_connector);
+		return false;
+	}
+
 	if (!intel_sdvo_create_enhance_property(intel_sdvo, intel_sdvo_connector))
 		goto err;
 
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 22cf0f4..b64fc1c6 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1189,8 +1189,8 @@
 	if (connector->polled & DRM_CONNECTOR_POLL_HPD) {
 		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 		i915_disable_pipestat(dev_priv, 0,
-				      PIPE_HOTPLUG_INTERRUPT_ENABLE |
-				      PIPE_HOTPLUG_TV_INTERRUPT_ENABLE);
+				      PIPE_HOTPLUG_INTERRUPT_STATUS |
+				      PIPE_HOTPLUG_TV_INTERRUPT_STATUS);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 	}
 
@@ -1266,8 +1266,8 @@
 	if (connector->polled & DRM_CONNECTOR_POLL_HPD) {
 		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 		i915_enable_pipestat(dev_priv, 0,
-				     PIPE_HOTPLUG_INTERRUPT_ENABLE |
-				     PIPE_HOTPLUG_TV_INTERRUPT_ENABLE);
+				     PIPE_HOTPLUG_INTERRUPT_STATUS |
+				     PIPE_HOTPLUG_TV_INTERRUPT_STATUS);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 	}
 
@@ -1634,6 +1634,7 @@
 	intel_encoder->disable = intel_disable_tv;
 	intel_encoder->get_hw_state = intel_tv_get_hw_state;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index c628414..7861d97 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -40,6 +40,12 @@
 
 #define __raw_posting_read(dev_priv__, reg__) (void)__raw_i915_read32(dev_priv__, reg__)
 
+static void
+assert_device_not_suspended(struct drm_i915_private *dev_priv)
+{
+	WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
+	     "Device suspended\n");
+}
 
 static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
 {
@@ -83,14 +89,14 @@
 	__gen6_gt_wait_for_thread_c0(dev_priv);
 }
 
-static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
+static void __gen7_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
 {
 	__raw_i915_write32(dev_priv, FORCEWAKE_MT, _MASKED_BIT_DISABLE(0xffff));
 	/* something from same cacheline, but !FORCEWAKE_MT */
 	__raw_posting_read(dev_priv, ECOBUS);
 }
 
-static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv,
+static void __gen7_gt_force_wake_mt_get(struct drm_i915_private *dev_priv,
 							int fw_engine)
 {
 	u32 forcewake_ack;
@@ -136,14 +142,16 @@
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
-static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv,
+static void __gen7_gt_force_wake_mt_put(struct drm_i915_private *dev_priv,
 							int fw_engine)
 {
 	__raw_i915_write32(dev_priv, FORCEWAKE_MT,
 			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
 	/* something from same cacheline, but !FORCEWAKE_MT */
 	__raw_posting_read(dev_priv, ECOBUS);
-	gen6_gt_check_fifodbg(dev_priv);
+
+	if (IS_GEN7(dev_priv->dev))
+		gen6_gt_check_fifodbg(dev_priv);
 }
 
 static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
@@ -251,16 +259,16 @@
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
-	if (FORCEWAKE_RENDER & fw_engine) {
-		if (dev_priv->uncore.fw_rendercount++ == 0)
-			dev_priv->uncore.funcs.force_wake_get(dev_priv,
-							FORCEWAKE_RENDER);
-	}
-	if (FORCEWAKE_MEDIA & fw_engine) {
-		if (dev_priv->uncore.fw_mediacount++ == 0)
-			dev_priv->uncore.funcs.force_wake_get(dev_priv,
-							FORCEWAKE_MEDIA);
-	}
+
+	if (fw_engine & FORCEWAKE_RENDER &&
+	    dev_priv->uncore.fw_rendercount++ != 0)
+		fw_engine &= ~FORCEWAKE_RENDER;
+	if (fw_engine & FORCEWAKE_MEDIA &&
+	    dev_priv->uncore.fw_mediacount++ != 0)
+		fw_engine &= ~FORCEWAKE_MEDIA;
+
+	if (fw_engine)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_engine);
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
@@ -272,46 +280,45 @@
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
-	if (FORCEWAKE_RENDER & fw_engine) {
-		WARN_ON(dev_priv->uncore.fw_rendercount == 0);
-		if (--dev_priv->uncore.fw_rendercount == 0)
-			dev_priv->uncore.funcs.force_wake_put(dev_priv,
-							FORCEWAKE_RENDER);
-	}
+	if (fw_engine & FORCEWAKE_RENDER &&
+	    --dev_priv->uncore.fw_rendercount != 0)
+		fw_engine &= ~FORCEWAKE_RENDER;
+	if (fw_engine & FORCEWAKE_MEDIA &&
+	    --dev_priv->uncore.fw_mediacount != 0)
+		fw_engine &= ~FORCEWAKE_MEDIA;
 
-	if (FORCEWAKE_MEDIA & fw_engine) {
-		WARN_ON(dev_priv->uncore.fw_mediacount == 0);
-		if (--dev_priv->uncore.fw_mediacount == 0)
-			dev_priv->uncore.funcs.force_wake_put(dev_priv,
-							FORCEWAKE_MEDIA);
-	}
+	if (fw_engine)
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, fw_engine);
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
-static void gen6_force_wake_work(struct work_struct *work)
+static void gen6_force_wake_timer(unsigned long arg)
 {
-	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), uncore.force_wake_work.work);
+	struct drm_i915_private *dev_priv = (void *)arg;
 	unsigned long irqflags;
 
+	assert_device_not_suspended(dev_priv);
+
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 	if (--dev_priv->uncore.forcewake_count == 0)
 		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 static void intel_uncore_forcewake_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (IS_VALLEYVIEW(dev)) {
+	if (IS_VALLEYVIEW(dev))
 		vlv_force_wake_reset(dev_priv);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
+	else if (IS_GEN6(dev) || IS_GEN7(dev))
 		__gen6_gt_force_wake_reset(dev_priv);
-		if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-			__gen6_gt_force_wake_mt_reset(dev_priv);
-	}
+
+	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_GEN8(dev))
+		__gen7_gt_force_wake_mt_reset(dev_priv);
 }
 
 void intel_uncore_early_sanitize(struct drm_device *dev)
@@ -354,7 +361,9 @@
 		mutex_lock(&dev_priv->rps.hw_lock);
 		reg_val = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS);
 
-		if (reg_val & (RENDER_PWRGT | MEDIA_PWRGT | DISP2D_PWRGT))
+		if (reg_val & (PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_RENDER) |
+			       PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_MEDIA) |
+			       PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_DISP2D)))
 			vlv_punit_write(dev_priv, PUNIT_REG_PWRGT_CTRL, 0x0);
 
 		mutex_unlock(&dev_priv->rps.hw_lock);
@@ -393,25 +402,38 @@
 void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
 {
 	unsigned long irqflags;
+	bool delayed = false;
 
 	if (!dev_priv->uncore.funcs.force_wake_put)
 		return;
 
 	/* Redirect to VLV specific routine */
-	if (IS_VALLEYVIEW(dev_priv->dev))
-		return vlv_force_wake_put(dev_priv, fw_engine);
+	if (IS_VALLEYVIEW(dev_priv->dev)) {
+		vlv_force_wake_put(dev_priv, fw_engine);
+		goto out;
+	}
 
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 	if (--dev_priv->uncore.forcewake_count == 0) {
 		dev_priv->uncore.forcewake_count++;
-		mod_delayed_work(dev_priv->wq,
-				 &dev_priv->uncore.force_wake_work,
-				 1);
+		delayed = true;
+		mod_timer_pinned(&dev_priv->uncore.force_wake_timer,
+				 jiffies + 1);
 	}
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
-	intel_runtime_pm_put(dev_priv);
+out:
+	if (!delayed)
+		intel_runtime_pm_put(dev_priv);
+}
+
+void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->uncore.funcs.force_wake_get)
+		return;
+
+	WARN_ON(dev_priv->uncore.forcewake_count > 0);
 }
 
 /* We give fast paths for the really cool registers */
@@ -446,16 +468,10 @@
 	}
 }
 
-static void
-assert_device_not_suspended(struct drm_i915_private *dev_priv)
-{
-	WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
-	     "Device suspended\n");
-}
-
 #define REG_READ_HEADER(x) \
 	unsigned long irqflags; \
 	u##x val = 0; \
+	assert_device_not_suspended(dev_priv); \
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags)
 
 #define REG_READ_FOOTER \
@@ -484,17 +500,15 @@
 static u##x \
 gen6_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	REG_READ_HEADER(x); \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		if (dev_priv->uncore.forcewake_count == 0) \
-			dev_priv->uncore.funcs.force_wake_get(dev_priv, \
-							FORCEWAKE_ALL); \
-		val = __raw_i915_read##x(dev_priv, reg); \
-		if (dev_priv->uncore.forcewake_count == 0) \
-			dev_priv->uncore.funcs.force_wake_put(dev_priv, \
-							FORCEWAKE_ALL); \
-	} else { \
-		val = __raw_i915_read##x(dev_priv, reg); \
+	if (dev_priv->uncore.forcewake_count == 0 && \
+	    NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, \
+						      FORCEWAKE_ALL); \
+		dev_priv->uncore.forcewake_count++; \
+		mod_timer_pinned(&dev_priv->uncore.force_wake_timer, \
+				 jiffies + 1); \
 	} \
+	val = __raw_i915_read##x(dev_priv, reg); \
 	REG_READ_FOOTER; \
 }
 
@@ -502,27 +516,19 @@
 static u##x \
 vlv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	unsigned fwengine = 0; \
-	unsigned *fwcount; \
 	REG_READ_HEADER(x); \
-	if (FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg)) {   \
-		fwengine = FORCEWAKE_RENDER;            \
-		fwcount = &dev_priv->uncore.fw_rendercount;    \
-	}                                               \
-	else if (FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)) {       \
-		fwengine = FORCEWAKE_MEDIA;             \
-		fwcount = &dev_priv->uncore.fw_mediacount;     \
+	if (FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg)) { \
+		if (dev_priv->uncore.fw_rendercount == 0) \
+			fwengine = FORCEWAKE_RENDER; \
+	} else if (FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)) { \
+		if (dev_priv->uncore.fw_mediacount == 0) \
+			fwengine = FORCEWAKE_MEDIA; \
 	}  \
-	if (fwengine != 0) {		\
-		if ((*fwcount)++ == 0) \
-			(dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
-								fwengine); \
-		val = __raw_i915_read##x(dev_priv, reg); \
-		if (--(*fwcount) == 0) \
-			(dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
-							fwengine); \
-	} else { \
-		val = __raw_i915_read##x(dev_priv, reg); \
-	} \
+	if (fwengine) \
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, fwengine); \
+	val = __raw_i915_read##x(dev_priv, reg); \
+	if (fwengine) \
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, fwengine); \
 	REG_READ_FOOTER; \
 }
 
@@ -554,6 +560,7 @@
 #define REG_WRITE_HEADER \
 	unsigned long irqflags; \
 	trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \
+	assert_device_not_suspended(dev_priv); \
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags)
 
 #define REG_WRITE_FOOTER \
@@ -584,7 +591,6 @@
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
-	assert_device_not_suspended(dev_priv); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	if (unlikely(__fifo_ret)) { \
 		gen6_gt_check_fifodbg(dev_priv); \
@@ -600,7 +606,6 @@
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
-	assert_device_not_suspended(dev_priv); \
 	hsw_unclaimed_reg_clear(dev_priv, reg); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	if (unlikely(__fifo_ret)) { \
@@ -634,16 +639,17 @@
 #define __gen8_write(x) \
 static void \
 gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
-	bool __needs_put = reg < 0x40000 && !is_gen8_shadowed(dev_priv, reg); \
 	REG_WRITE_HEADER; \
-	if (__needs_put) { \
-		dev_priv->uncore.funcs.force_wake_get(dev_priv, \
-							FORCEWAKE_ALL); \
-	} \
-	__raw_i915_write##x(dev_priv, reg, val); \
-	if (__needs_put) { \
-		dev_priv->uncore.funcs.force_wake_put(dev_priv, \
-							FORCEWAKE_ALL); \
+	if (reg < 0x40000 && !is_gen8_shadowed(dev_priv, reg)) { \
+		if (dev_priv->uncore.forcewake_count == 0) \
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,	\
+							      FORCEWAKE_ALL); \
+		__raw_i915_write##x(dev_priv, reg, val); \
+		if (dev_priv->uncore.forcewake_count == 0) \
+			dev_priv->uncore.funcs.force_wake_put(dev_priv, \
+							      FORCEWAKE_ALL); \
+	} else { \
+		__raw_i915_write##x(dev_priv, reg, val); \
 	} \
 	REG_WRITE_FOOTER; \
 }
@@ -681,15 +687,15 @@
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	INIT_DELAYED_WORK(&dev_priv->uncore.force_wake_work,
-			  gen6_force_wake_work);
+	setup_timer(&dev_priv->uncore.force_wake_timer,
+		    gen6_force_wake_timer, (unsigned long)dev_priv);
 
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __vlv_force_wake_get;
 		dev_priv->uncore.funcs.force_wake_put = __vlv_force_wake_put;
 	} else if (IS_HASWELL(dev) || IS_GEN8(dev)) {
-		dev_priv->uncore.funcs.force_wake_get = __gen6_gt_force_wake_mt_get;
-		dev_priv->uncore.funcs.force_wake_put = __gen6_gt_force_wake_mt_put;
+		dev_priv->uncore.funcs.force_wake_get = __gen7_gt_force_wake_mt_get;
+		dev_priv->uncore.funcs.force_wake_put = __gen7_gt_force_wake_mt_put;
 	} else if (IS_IVYBRIDGE(dev)) {
 		u32 ecobus;
 
@@ -703,16 +709,16 @@
 		 * forcewake being disabled.
 		 */
 		mutex_lock(&dev->struct_mutex);
-		__gen6_gt_force_wake_mt_get(dev_priv, FORCEWAKE_ALL);
+		__gen7_gt_force_wake_mt_get(dev_priv, FORCEWAKE_ALL);
 		ecobus = __raw_i915_read32(dev_priv, ECOBUS);
-		__gen6_gt_force_wake_mt_put(dev_priv, FORCEWAKE_ALL);
+		__gen7_gt_force_wake_mt_put(dev_priv, FORCEWAKE_ALL);
 		mutex_unlock(&dev->struct_mutex);
 
 		if (ecobus & FORCEWAKE_MT_ENABLE) {
 			dev_priv->uncore.funcs.force_wake_get =
-				__gen6_gt_force_wake_mt_get;
+				__gen7_gt_force_wake_mt_get;
 			dev_priv->uncore.funcs.force_wake_put =
-				__gen6_gt_force_wake_mt_put;
+				__gen7_gt_force_wake_mt_put;
 		} else {
 			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
 			DRM_INFO("when using vblank-synced partial screen updates.\n");
@@ -794,10 +800,11 @@
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	flush_delayed_work(&dev_priv->uncore.force_wake_work);
+	del_timer_sync(&dev_priv->uncore.force_wake_timer);
 
 	/* Paranoia: make sure we have disabled everything before we exit. */
 	intel_uncore_sanitize(dev);
+	intel_uncore_forcewake_reset(dev);
 }
 
 static const struct register_whitelist {
@@ -947,6 +954,7 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int	ret;
 	unsigned long irqflags;
+	u32 fw_engine = 0;
 
 	/* Hold uncore.lock across reset to prevent any register access
 	 * with forcewake not set correctly
@@ -966,14 +974,25 @@
 
 	intel_uncore_forcewake_reset(dev);
 
-	/* If reset with a user forcewake, try to restore, otherwise turn it off */
-	if (dev_priv->uncore.forcewake_count)
-		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
-	else
-		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
+	/* If reset with a user forcewake, try to restore */
+	if (IS_VALLEYVIEW(dev)) {
+		if (dev_priv->uncore.fw_rendercount)
+			fw_engine |= FORCEWAKE_RENDER;
 
-	/* Restore fifo count */
-	dev_priv->uncore.fifo_count = __raw_i915_read32(dev_priv, GTFIFOCTL) & GT_FIFO_FREE_ENTRIES_MASK;
+		if (dev_priv->uncore.fw_mediacount)
+			fw_engine |= FORCEWAKE_MEDIA;
+	} else {
+		if (dev_priv->uncore.forcewake_count)
+			fw_engine = FORCEWAKE_ALL;
+	}
+
+	if (fw_engine)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_engine);
+
+	if (IS_GEN6(dev) || IS_GEN7(dev))
+		dev_priv->uncore.fifo_count =
+			__raw_i915_read32(dev_priv, GTFIFOCTL) &
+			GT_FIFO_FREE_ENTRIES_MASK;
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 	return ret;
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index adb5166..5a00e90 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -259,7 +259,9 @@
 
 	ret = ttm_bo_device_init(&mdev->ttm.bdev,
 				 mdev->ttm.bo_global_ref.ref.object,
-				 &mgag200_bo_driver, DRM_FILE_PAGE_OFFSET,
+				 &mgag200_bo_driver,
+				 dev->anon_inode->i_mapping,
+				 DRM_FILE_PAGE_OFFSET,
 				 true);
 	if (ret) {
 		DRM_ERROR("Error initialising bo driver; %d\n", ret);
@@ -324,7 +326,6 @@
 	}
 
 	mgabo->bo.bdev = &mdev->ttm.bdev;
-	mgabo->bo.bdev->dev_mapping = dev->dev_mapping;
 
 	mgag200_ttm_placement(mgabo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 27c3fd8..c90c0dc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -228,8 +228,6 @@
 	struct nouveau_bo *nvbo = NULL;
 	int ret = 0;
 
-	drm->ttm.bdev.dev_mapping = drm->dev->dev_mapping;
-
 	if (!pfb->memtype_valid(pfb, req->info.tile_flags)) {
 		NV_ERROR(cli, "bad page flags: 0x%08x\n", req->info.tile_flags);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index d45d50d..be3a3c9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -376,7 +376,9 @@
 
 	ret = ttm_bo_device_init(&drm->ttm.bdev,
 				  drm->ttm.bo_global_ref.ref.object,
-				  &nouveau_bo_driver, DRM_FILE_PAGE_OFFSET,
+				  &nouveau_bo_driver,
+				  dev->anon_inode->i_mapping,
+				  DRM_FILE_PAGE_OFFSET,
 				  bits <= 32 ? true : false);
 	if (ret) {
 		NV_ERROR(drm, "error initialising bo driver, %d\n", ret);
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 5aec3e8..c8d9727 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -153,24 +153,24 @@
 static void evict_entry(struct drm_gem_object *obj,
 		enum tiler_fmt fmt, struct usergart_entry *entry)
 {
-	if (obj->dev->dev_mapping) {
-		struct omap_gem_object *omap_obj = to_omap_bo(obj);
-		int n = usergart[fmt].height;
-		size_t size = PAGE_SIZE * n;
-		loff_t off = mmap_offset(obj) +
-				(entry->obj_pgoff << PAGE_SHIFT);
-		const int m = 1 + ((omap_obj->width << fmt) / PAGE_SIZE);
-		if (m > 1) {
-			int i;
-			/* if stride > than PAGE_SIZE then sparse mapping: */
-			for (i = n; i > 0; i--) {
-				unmap_mapping_range(obj->dev->dev_mapping,
-						off, PAGE_SIZE, 1);
-				off += PAGE_SIZE * m;
-			}
-		} else {
-			unmap_mapping_range(obj->dev->dev_mapping, off, size, 1);
+	struct omap_gem_object *omap_obj = to_omap_bo(obj);
+	int n = usergart[fmt].height;
+	size_t size = PAGE_SIZE * n;
+	loff_t off = mmap_offset(obj) +
+			(entry->obj_pgoff << PAGE_SHIFT);
+	const int m = 1 + ((omap_obj->width << fmt) / PAGE_SIZE);
+
+	if (m > 1) {
+		int i;
+		/* if stride > than PAGE_SIZE then sparse mapping: */
+		for (i = n; i > 0; i--) {
+			unmap_mapping_range(obj->dev->anon_inode->i_mapping,
+					    off, PAGE_SIZE, 1);
+			off += PAGE_SIZE * m;
 		}
+	} else {
+		unmap_mapping_range(obj->dev->anon_inode->i_mapping,
+				    off, size, 1);
 	}
 
 	entry->obj = NULL;
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index 8691c76..b95f144 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -82,8 +82,6 @@
 	enum ttm_bo_type type;
 	int r;
 
-	if (unlikely(qdev->mman.bdev.dev_mapping == NULL))
-		qdev->mman.bdev.dev_mapping = qdev->ddev->dev_mapping;
 	if (kernel)
 		type = ttm_bo_type_kernel;
 	else
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index c7e7e65..29c02e0 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -493,7 +493,9 @@
 	/* No others user of address space so set it to 0 */
 	r = ttm_bo_device_init(&qdev->mman.bdev,
 			       qdev->mman.bo_global_ref.ref.object,
-			       &qxl_bo_driver, DRM_FILE_PAGE_OFFSET, 0);
+			       &qxl_bo_driver,
+			       qdev->ddev->anon_inode->i_mapping,
+			       DRM_FILE_PAGE_OFFSET, 0);
 	if (r) {
 		DRM_ERROR("failed initializing buffer object driver(%d).\n", r);
 		return r;
@@ -518,8 +520,6 @@
 		 ((unsigned)num_io_pages * PAGE_SIZE) / (1024 * 1024));
 	DRM_INFO("qxl: %uM of Surface memory size\n",
 		 (unsigned)qdev->surfaceram_size / (1024 * 1024));
-	if (unlikely(qdev->mman.bdev.dev_mapping == NULL))
-		qdev->mman.bdev.dev_mapping = qdev->ddev->dev_mapping;
 	r = qxl_ttm_debugfs_init(qdev);
 	if (r) {
 		DRM_ERROR("Failed to init debugfs\n");
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index ed60caa..0943353 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -80,7 +80,7 @@
 	r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
 	rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o \
 	trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
-	ci_dpm.o dce6_afmt.o
+	ci_dpm.o dce6_afmt.o radeon_vm.o
 
 # add async DMA block
 radeon-y += \
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 0d19f4f..daa4dd3 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1774,6 +1774,20 @@
 			return ATOM_PPLL1;
 		DRM_ERROR("unable to allocate a PPLL\n");
 		return ATOM_PPLL_INVALID;
+	} else if (ASIC_IS_DCE41(rdev)) {
+		/* Don't share PLLs on DCE4.1 chips */
+		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+			if (rdev->clock.dp_extclk)
+				/* skip PPLL programming if using ext clock */
+				return ATOM_PPLL_INVALID;
+		}
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
+			return ATOM_PPLL1;
+		if (!(pll_in_use & (1 << ATOM_PPLL2)))
+			return ATOM_PPLL2;
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
 	} else if (ASIC_IS_DCE4(rdev)) {
 		/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
 		 * depending on the asic:
@@ -1801,7 +1815,7 @@
 				if (pll != ATOM_PPLL_INVALID)
 					return pll;
 			}
-		} else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */
+		} else {
 			/* use the same PPLL for all monitors with the same clock */
 			pll = radeon_get_shared_nondp_ppll(crtc);
 			if (pll != ATOM_PPLL_INVALID)
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 2cec2ab..607dc14 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1314,7 +1314,7 @@
 			}
 			if (is_dp)
 				args.v5.ucLaneNum = dp_lane_count;
-			else if (radeon_encoder->pixel_clock > 165000)
+			else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
 				args.v5.ucLaneNum = 8;
 			else
 				args.v5.ucLaneNum = 4;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 92e38b5..0ae991d 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3047,7 +3047,7 @@
 }
 
 /**
- * cik_select_se_sh - select which SE, SH to address
+ * cik_get_rb_disabled - computes the mask of disabled RBs
  *
  * @rdev: radeon_device pointer
  * @max_rb_num: max RBs (render backends) for the asic
@@ -4133,8 +4133,11 @@
 {
 	if (enable)
 		WREG32(CP_MEC_CNTL, 0);
-	else
+	else {
 		WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT));
+		rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false;
+		rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;
+	}
 	udelay(50);
 }
 
@@ -7949,7 +7952,8 @@
 	/* init golden registers */
 	cik_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = cik_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 00150ac..89b4afa 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -264,6 +264,8 @@
 		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
 		WREG32(SDMA0_GFX_IB_CNTL + reg_offset, 0);
 	}
+	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
 }
 
 /**
@@ -291,6 +293,11 @@
 	u32 me_cntl, reg_offset;
 	int i;
 
+	if (enable == false) {
+		cik_sdma_gfx_stop(rdev);
+		cik_sdma_rlc_stop(rdev);
+	}
+
 	for (i = 0; i < 2; i++) {
 		if (i == 0)
 			reg_offset = SDMA0_REGISTER_OFFSET;
@@ -418,10 +425,6 @@
 	if (!rdev->sdma_fw)
 		return -EINVAL;
 
-	/* stop the gfx rings and rlc compute queues */
-	cik_sdma_gfx_stop(rdev);
-	cik_sdma_rlc_stop(rdev);
-
 	/* halt the MEs */
 	cik_sdma_enable(rdev, false);
 
@@ -490,9 +493,6 @@
  */
 void cik_sdma_fini(struct radeon_device *rdev)
 {
-	/* stop the gfx rings and rlc compute queues */
-	cik_sdma_gfx_stop(rdev);
-	cik_sdma_rlc_stop(rdev);
 	/* halt the MEs */
 	cik_sdma_enable(rdev, false);
 	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 713a5d3..94e8587 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -278,13 +278,15 @@
 	return !ASIC_IS_NODCE(rdev);
 }
 
-static void dce6_audio_enable(struct radeon_device *rdev,
-			      struct r600_audio_pin *pin,
-			      bool enable)
+void dce6_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable)
 {
+	if (!pin)
+		return;
+
 	WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL,
-			AUDIO_ENABLED);
-	DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
+			enable ? AUDIO_ENABLED : 0);
 }
 
 static const u32 pin_offsets[7] =
@@ -323,7 +325,8 @@
 		rdev->audio.pin[i].connected = false;
 		rdev->audio.pin[i].offset = pin_offsets[i];
 		rdev->audio.pin[i].id = i;
-		dce6_audio_enable(rdev, &rdev->audio.pin[i], true);
+		/* disable audio.  it will be set up later */
+		dce6_audio_enable(rdev, &rdev->audio.pin[i], false);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index b1f1253..b406546 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -5295,7 +5295,8 @@
 	/* init golden registers */
 	evergreen_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = evergreen_startup(rdev);
@@ -5471,9 +5472,9 @@
 	radeon_wb_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	evergreen_pcie_gart_fini(rdev);
 	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
+	evergreen_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
 	radeon_fence_driver_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index c7cac07..5c8b358 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -1165,7 +1165,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case DB_DEPTH_CONTROL:
 		track->db_depth_control = radeon_get_ib_value(p, idx);
@@ -1196,12 +1196,12 @@
 			}
 			ib[idx] &= ~Z_ARRAY_MODE(0xf);
 			track->db_z_info &= ~Z_ARRAY_MODE(0xf);
-			ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
-			track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+			ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
+			track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
+			if (reloc->tiling_flags & RADEON_TILING_MACRO) {
 				unsigned bankw, bankh, mtaspect, tile_split;
 
-				evergreen_tiling_fields(reloc->lobj.tiling_flags,
+				evergreen_tiling_fields(reloc->tiling_flags,
 							&bankw, &bankh, &mtaspect,
 							&tile_split);
 				ib[idx] |= DB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
@@ -1237,7 +1237,7 @@
 			return -EINVAL;
 		}
 		track->db_z_read_offset = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->db_z_read_bo = reloc->robj;
 		track->db_dirty = true;
 		break;
@@ -1249,7 +1249,7 @@
 			return -EINVAL;
 		}
 		track->db_z_write_offset = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->db_z_write_bo = reloc->robj;
 		track->db_dirty = true;
 		break;
@@ -1261,7 +1261,7 @@
 			return -EINVAL;
 		}
 		track->db_s_read_offset = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->db_s_read_bo = reloc->robj;
 		track->db_dirty = true;
 		break;
@@ -1273,7 +1273,7 @@
 			return -EINVAL;
 		}
 		track->db_s_write_offset = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->db_s_write_bo = reloc->robj;
 		track->db_dirty = true;
 		break;
@@ -1297,7 +1297,7 @@
 		}
 		tmp = (reg - VGT_STRMOUT_BUFFER_BASE_0) / 16;
 		track->vgt_strmout_bo_offset[tmp] = radeon_get_ib_value(p, idx) << 8;
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->vgt_strmout_bo[tmp] = reloc->robj;
 		track->streamout_dirty = true;
 		break;
@@ -1317,7 +1317,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 	case CB_TARGET_MASK:
 		track->cb_target_mask = radeon_get_ib_value(p, idx);
 		track->cb_dirty = true;
@@ -1381,8 +1381,8 @@
 						"0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
+			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
 		}
 		track->cb_dirty = true;
 		break;
@@ -1399,8 +1399,8 @@
 						"0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
+			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
 		}
 		track->cb_dirty = true;
 		break;
@@ -1461,10 +1461,10 @@
 			return -EINVAL;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+			if (reloc->tiling_flags & RADEON_TILING_MACRO) {
 				unsigned bankw, bankh, mtaspect, tile_split;
 
-				evergreen_tiling_fields(reloc->lobj.tiling_flags,
+				evergreen_tiling_fields(reloc->tiling_flags,
 							&bankw, &bankh, &mtaspect,
 							&tile_split);
 				ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
@@ -1489,10 +1489,10 @@
 			return -EINVAL;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+			if (reloc->tiling_flags & RADEON_TILING_MACRO) {
 				unsigned bankw, bankh, mtaspect, tile_split;
 
-				evergreen_tiling_fields(reloc->lobj.tiling_flags,
+				evergreen_tiling_fields(reloc->tiling_flags,
 							&bankw, &bankh, &mtaspect,
 							&tile_split);
 				ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
@@ -1520,7 +1520,7 @@
 			dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->cb_color_fmask_bo[tmp] = reloc->robj;
 		break;
 	case CB_COLOR0_CMASK:
@@ -1537,7 +1537,7 @@
 			dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->cb_color_cmask_bo[tmp] = reloc->robj;
 		break;
 	case CB_COLOR0_FMASK_SLICE:
@@ -1578,7 +1578,7 @@
 		}
 		tmp = (reg - CB_COLOR0_BASE) / 0x3c;
 		track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->cb_color_bo[tmp] = reloc->robj;
 		track->cb_dirty = true;
 		break;
@@ -1594,7 +1594,7 @@
 		}
 		tmp = ((reg - CB_COLOR8_BASE) / 0x1c) + 8;
 		track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->cb_color_bo[tmp] = reloc->robj;
 		track->cb_dirty = true;
 		break;
@@ -1606,7 +1606,7 @@
 			return -EINVAL;
 		}
 		track->htile_offset = radeon_get_ib_value(p, idx);
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->htile_bo = reloc->robj;
 		track->db_dirty = true;
 		break;
@@ -1723,7 +1723,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SX_MEMORY_EXPORT_BASE:
 		if (p->rdev->family >= CHIP_CAYMAN) {
@@ -1737,7 +1737,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case CAYMAN_SX_SCATTER_EXPORT_BASE:
 		if (p->rdev->family < CHIP_CAYMAN) {
@@ -1751,7 +1751,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SX_MISC:
 		track->sx_misc_kill_all_prims = (radeon_get_ib_value(p, idx) & 0x1) != 0;
@@ -1836,7 +1836,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         (idx_value & 0xfffffff0) +
 		         ((u64)(tmp & 0xff) << 32);
 
@@ -1882,7 +1882,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         idx_value +
 		         ((u64)(radeon_get_ib_value(p, idx+1) & 0xff) << 32);
 
@@ -1909,7 +1909,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         idx_value +
 		         ((u64)(radeon_get_ib_value(p, idx+1) & 0xff) << 32);
 
@@ -1937,7 +1937,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         radeon_get_ib_value(p, idx+1) +
 		         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -2027,7 +2027,7 @@
 			DRM_ERROR("bad DISPATCH_INDIRECT\n");
 			return -EINVAL;
 		}
-		ib[idx+0] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
+		ib[idx+0] = idx_value + (u32)(reloc->gpu_offset & 0xffffffff);
 		r = evergreen_cs_track_check(p);
 		if (r) {
 			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
@@ -2049,7 +2049,7 @@
 				return -EINVAL;
 			}
 
-			offset = reloc->lobj.gpu_offset +
+			offset = reloc->gpu_offset +
 			         (radeon_get_ib_value(p, idx+1) & 0xfffffffc) +
 			         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -2106,7 +2106,7 @@
 				tmp = radeon_get_ib_value(p, idx) +
 					((u64)(radeon_get_ib_value(p, idx+1) & 0xff) << 32);
 
-				offset = reloc->lobj.gpu_offset + tmp;
+				offset = reloc->gpu_offset + tmp;
 
 				if ((tmp + size) > radeon_bo_size(reloc->robj)) {
 					dev_warn(p->dev, "CP DMA src buffer too small (%llu %lu)\n",
@@ -2144,7 +2144,7 @@
 				tmp = radeon_get_ib_value(p, idx+2) +
 					((u64)(radeon_get_ib_value(p, idx+3) & 0xff) << 32);
 
-				offset = reloc->lobj.gpu_offset + tmp;
+				offset = reloc->gpu_offset + tmp;
 
 				if ((tmp + size) > radeon_bo_size(reloc->robj)) {
 					dev_warn(p->dev, "CP DMA dst buffer too small (%llu %lu)\n",
@@ -2174,7 +2174,7 @@
 				DRM_ERROR("bad SURFACE_SYNC\n");
 				return -EINVAL;
 			}
-			ib[idx+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+			ib[idx+2] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		}
 		break;
 	case PACKET3_EVENT_WRITE:
@@ -2190,7 +2190,7 @@
 				DRM_ERROR("bad EVENT_WRITE\n");
 				return -EINVAL;
 			}
-			offset = reloc->lobj.gpu_offset +
+			offset = reloc->gpu_offset +
 			         (radeon_get_ib_value(p, idx+1) & 0xfffffff8) +
 			         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -2212,7 +2212,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         (radeon_get_ib_value(p, idx+1) & 0xfffffffc) +
 		         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -2234,7 +2234,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         (radeon_get_ib_value(p, idx+1) & 0xfffffffc) +
 		         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -2302,11 +2302,11 @@
 				}
 				if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
 					ib[idx+1+(i*8)+1] |=
-						TEX_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
-					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+						TEX_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
+					if (reloc->tiling_flags & RADEON_TILING_MACRO) {
 						unsigned bankw, bankh, mtaspect, tile_split;
 
-						evergreen_tiling_fields(reloc->lobj.tiling_flags,
+						evergreen_tiling_fields(reloc->tiling_flags,
 									&bankw, &bankh, &mtaspect,
 									&tile_split);
 						ib[idx+1+(i*8)+6] |= TEX_TILE_SPLIT(tile_split);
@@ -2318,7 +2318,7 @@
 					}
 				}
 				texture = reloc->robj;
-				toffset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+				toffset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 
 				/* tex mip base */
 				tex_dim = ib[idx+1+(i*8)+0] & 0x7;
@@ -2337,7 +2337,7 @@
 						DRM_ERROR("bad SET_RESOURCE (tex)\n");
 						return -EINVAL;
 					}
-					moffset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+					moffset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 					mipmap = reloc->robj;
 				}
 
@@ -2364,7 +2364,7 @@
 					ib[idx+1+(i*8)+1] = radeon_bo_size(reloc->robj) - offset;
 				}
 
-				offset64 = reloc->lobj.gpu_offset + offset;
+				offset64 = reloc->gpu_offset + offset;
 				ib[idx+1+(i*8)+0] = offset64;
 				ib[idx+1+(i*8)+2] = (ib[idx+1+(i*8)+2] & 0xffffff00) |
 						    (upper_32_bits(offset64) & 0xff);
@@ -2445,7 +2445,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+1] = offset;
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		}
@@ -2464,7 +2464,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+3] = offset;
 			ib[idx+4] = upper_32_bits(offset) & 0xff;
 		}
@@ -2493,7 +2493,7 @@
 				  offset + 8, radeon_bo_size(reloc->robj));
 			return -EINVAL;
 		}
-		offset += reloc->lobj.gpu_offset;
+		offset += reloc->gpu_offset;
 		ib[idx+0] = offset;
 		ib[idx+1] = upper_32_bits(offset) & 0xff;
 		break;
@@ -2518,7 +2518,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+1] = offset;
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		} else {
@@ -2542,7 +2542,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+3] = offset;
 			ib[idx+4] = upper_32_bits(offset) & 0xff;
 		} else {
@@ -2717,7 +2717,7 @@
 				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset <<= 8;
 
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				p->idx += count + 7;
 				break;
 			/* linear */
@@ -2725,8 +2725,8 @@
 				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+2] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 				p->idx += count + 3;
 				break;
 			default:
@@ -2768,10 +2768,10 @@
 							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-				ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+2] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+3] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
+				ib[idx+4] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 				p->idx += 5;
 				break;
 			/* Copy L2T/T2L */
@@ -2781,22 +2781,22 @@
 					/* tiled src, linear dst */
 					src_offset = radeon_get_ib_value(p, idx+1);
 					src_offset <<= 8;
-					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8);
 
 					dst_offset = radeon_get_ib_value(p, idx + 7);
 					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
-					ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+7] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 				} else {
 					/* linear src, tiled dst */
 					src_offset = radeon_get_ib_value(p, idx+7);
 					src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
-					ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+7] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 
 					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset <<= 8;
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				}
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 					dev_warn(p->dev, "DMA L2T, src buffer too small (%llu %lu)\n",
@@ -2827,10 +2827,10 @@
 							dst_offset + count, radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xffffffff);
-				ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xffffffff);
-				ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-				ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xffffffff);
+				ib[idx+2] += (u32)(src_reloc->gpu_offset & 0xffffffff);
+				ib[idx+3] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
+				ib[idx+4] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 				p->idx += 5;
 				break;
 			/* Copy L2L, partial */
@@ -2840,10 +2840,10 @@
 					DRM_ERROR("L2L Partial is cayman only !\n");
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset & 0xffffffff);
-				ib[idx+2] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-				ib[idx+4] += (u32)(dst_reloc->lobj.gpu_offset & 0xffffffff);
-				ib[idx+5] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(src_reloc->gpu_offset & 0xffffffff);
+				ib[idx+2] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
+				ib[idx+4] += (u32)(dst_reloc->gpu_offset & 0xffffffff);
+				ib[idx+5] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 
 				p->idx += 9;
 				break;
@@ -2876,12 +2876,12 @@
 							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+3] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+4] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-				ib[idx+5] += upper_32_bits(dst2_reloc->lobj.gpu_offset) & 0xff;
-				ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+2] += (u32)(dst2_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+3] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+4] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
+				ib[idx+5] += upper_32_bits(dst2_reloc->gpu_offset) & 0xff;
+				ib[idx+6] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 				p->idx += 7;
 				break;
 			/* Copy L2T Frame to Field */
@@ -2916,10 +2916,10 @@
 							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
-				ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
+				ib[idx+2] += (u32)(dst2_reloc->gpu_offset >> 8);
+				ib[idx+8] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+9] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 				p->idx += 10;
 				break;
 			/* Copy L2T/T2L, partial */
@@ -2932,16 +2932,16 @@
 				/* detile bit */
 				if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) {
 					/* tiled src, linear dst */
-					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8);
 
-					ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+7] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 				} else {
 					/* linear src, tiled dst */
-					ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+7] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				}
 				p->idx += 12;
 				break;
@@ -2978,10 +2978,10 @@
 							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
-				ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
+				ib[idx+2] += (u32)(dst2_reloc->gpu_offset >> 8);
+				ib[idx+8] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+9] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 				p->idx += 10;
 				break;
 			/* Copy L2T/T2L (tile units) */
@@ -2992,22 +2992,22 @@
 					/* tiled src, linear dst */
 					src_offset = radeon_get_ib_value(p, idx+1);
 					src_offset <<= 8;
-					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8);
 
 					dst_offset = radeon_get_ib_value(p, idx+7);
 					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
-					ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+7] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 				} else {
 					/* linear src, tiled dst */
 					src_offset = radeon_get_ib_value(p, idx+7);
 					src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
-					ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+7] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+8] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 
 					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset <<= 8;
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				}
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 					dev_warn(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n",
@@ -3028,8 +3028,8 @@
 					DRM_ERROR("L2T, T2L Partial is cayman only !\n");
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
-				ib[idx+4] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8);
+				ib[idx+4] += (u32)(dst_reloc->gpu_offset >> 8);
 				p->idx += 13;
 				break;
 			/* Copy L2T broadcast (tile units) */
@@ -3065,10 +3065,10 @@
 							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
-				ib[idx+2] += (u32)(dst2_reloc->lobj.gpu_offset >> 8);
-				ib[idx+8] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+9] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
+				ib[idx+2] += (u32)(dst2_reloc->gpu_offset >> 8);
+				ib[idx+8] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+9] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 				p->idx += 10;
 				break;
 			default:
@@ -3089,8 +3089,8 @@
 					 dst_offset, radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
-			ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-			ib[idx+3] += (upper_32_bits(dst_reloc->lobj.gpu_offset) << 16) & 0x00ff0000;
+			ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+			ib[idx+3] += (upper_32_bits(dst_reloc->gpu_offset) << 16) & 0x00ff0000;
 			p->idx += 4;
 			break;
 		case DMA_PACKET_NOP:
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 0c6d5ce..05b0c95 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -306,6 +306,15 @@
 		return;
 	offset = dig->afmt->offset;
 
+	/* disable audio prior to setting up hw */
+	if (ASIC_IS_DCE6(rdev)) {
+		dig->afmt->pin = dce6_audio_get_pin(rdev);
+		dce6_audio_enable(rdev, dig->afmt->pin, false);
+	} else {
+		dig->afmt->pin = r600_audio_get_pin(rdev);
+		r600_audio_enable(rdev, dig->afmt->pin, false);
+	}
+
 	evergreen_audio_set_dto(encoder, mode->clock);
 
 	WREG32(HDMI_VBI_PACKET_CONTROL + offset,
@@ -409,12 +418,16 @@
 	WREG32(AFMT_RAMP_CONTROL1 + offset, 0x007FFFFF);
 	WREG32(AFMT_RAMP_CONTROL2 + offset, 0x00000001);
 	WREG32(AFMT_RAMP_CONTROL3 + offset, 0x00000001);
+
+	/* enable audio after to setting up hw */
+	if (ASIC_IS_DCE6(rdev))
+		dce6_audio_enable(rdev, dig->afmt->pin, true);
+	else
+		r600_audio_enable(rdev, dig->afmt->pin, true);
 }
 
 void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 {
-	struct drm_device *dev = encoder->dev;
-	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 
@@ -427,15 +440,6 @@
 	if (!enable && !dig->afmt->enabled)
 		return;
 
-	if (enable) {
-		if (ASIC_IS_DCE6(rdev))
-			dig->afmt->pin = dce6_audio_get_pin(rdev);
-		else
-			dig->afmt->pin = r600_audio_get_pin(rdev);
-	} else {
-		dig->afmt->pin = NULL;
-	}
-
 	dig->afmt->enabled = enable;
 
 	DRM_DEBUG("%sabling HDMI interface @ 0x%04X for encoder 0x%x\n",
diff --git a/drivers/gpu/drm/radeon/evergreen_smc.h b/drivers/gpu/drm/radeon/evergreen_smc.h
index 76ada8c..3a03ba3 100644
--- a/drivers/gpu/drm/radeon/evergreen_smc.h
+++ b/drivers/gpu/drm/radeon/evergreen_smc.h
@@ -57,7 +57,7 @@
 
 #define EVERGREEN_SMC_FIRMWARE_HEADER_LOCATION 0x100
 
-#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters   0x0
+#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters   0x8
 #define EVERGREEN_SMC_FIRMWARE_HEADER_stateTable      0xC
 #define EVERGREEN_SMC_FIRMWARE_HEADER_mcRegisterTable 0x20
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 85168ec..d246e04 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -2103,7 +2103,8 @@
 	/* init golden registers */
 	ni_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = cayman_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 1690a2d..030f8e4 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1274,12 +1274,12 @@
 
 	value = radeon_get_ib_value(p, idx);
 	tmp = value & 0x003fffff;
-	tmp += (((u32)reloc->lobj.gpu_offset) >> 10);
+	tmp += (((u32)reloc->gpu_offset) >> 10);
 
 	if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+		if (reloc->tiling_flags & RADEON_TILING_MACRO)
 			tile_flags |= RADEON_DST_TILE_MACRO;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+		if (reloc->tiling_flags & RADEON_TILING_MICRO) {
 			if (reg == RADEON_SRC_PITCH_OFFSET) {
 				DRM_ERROR("Cannot src blit from microtiled surface\n");
 				radeon_cs_dump_packet(p, pkt);
@@ -1325,7 +1325,7 @@
 			return r;
 		}
 		idx_value = radeon_get_ib_value(p, idx);
-		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
+		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->gpu_offset);
 
 		track->arrays[i + 0].esize = idx_value >> 8;
 		track->arrays[i + 0].robj = reloc->robj;
@@ -1337,7 +1337,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx+2] = radeon_get_ib_value(p, idx + 2) + ((u32)reloc->lobj.gpu_offset);
+		ib[idx+2] = radeon_get_ib_value(p, idx + 2) + ((u32)reloc->gpu_offset);
 		track->arrays[i + 1].robj = reloc->robj;
 		track->arrays[i + 1].esize = idx_value >> 24;
 		track->arrays[i + 1].esize &= 0x7F;
@@ -1351,7 +1351,7 @@
 			return r;
 		}
 		idx_value = radeon_get_ib_value(p, idx);
-		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
+		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->gpu_offset);
 		track->arrays[i + 0].robj = reloc->robj;
 		track->arrays[i + 0].esize = idx_value >> 8;
 		track->arrays[i + 0].esize &= 0x7F;
@@ -1594,7 +1594,7 @@
 		track->zb.robj = reloc->robj;
 		track->zb.offset = idx_value;
 		track->zb_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case RADEON_RB3D_COLOROFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
@@ -1607,7 +1607,7 @@
 		track->cb[0].robj = reloc->robj;
 		track->cb[0].offset = idx_value;
 		track->cb_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case RADEON_PP_TXOFFSET_0:
 	case RADEON_PP_TXOFFSET_1:
@@ -1621,16 +1621,16 @@
 			return r;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= RADEON_TXO_MACRO_TILE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= RADEON_TXO_MICRO_TILE_X2;
 
 			tmp = idx_value & ~(0x7 << 2);
 			tmp |= tile_flags;
-			ib[idx] = tmp + ((u32)reloc->lobj.gpu_offset);
+			ib[idx] = tmp + ((u32)reloc->gpu_offset);
 		} else
-			ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+			ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		track->textures[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -1648,7 +1648,7 @@
 			return r;
 		}
 		track->textures[0].cube_info[i].offset = idx_value;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		track->textures[0].cube_info[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -1666,7 +1666,7 @@
 			return r;
 		}
 		track->textures[1].cube_info[i].offset = idx_value;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		track->textures[1].cube_info[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -1684,7 +1684,7 @@
 			return r;
 		}
 		track->textures[2].cube_info[i].offset = idx_value;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		track->textures[2].cube_info[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -1702,9 +1702,9 @@
 			return r;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= RADEON_COLOR_TILE_ENABLE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
 
 			tmp = idx_value & ~(0x7 << 16);
@@ -1772,7 +1772,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case RADEON_PP_CNTL:
 		{
@@ -1932,7 +1932,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx+1] = radeon_get_ib_value(p, idx+1) + ((u32)reloc->lobj.gpu_offset);
+		ib[idx+1] = radeon_get_ib_value(p, idx+1) + ((u32)reloc->gpu_offset);
 		r = r100_cs_track_check_pkt3_indx_buffer(p, pkt, reloc->robj);
 		if (r) {
 			return r;
@@ -1946,7 +1946,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx] = radeon_get_ib_value(p, idx) + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = radeon_get_ib_value(p, idx) + ((u32)reloc->gpu_offset);
 		track->num_arrays = 1;
 		track->vtx_size = r100_get_vtx_size(radeon_get_ib_value(p, idx + 2));
 
@@ -3939,8 +3939,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r100_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index b3807ed..58f0473 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -185,7 +185,7 @@
 		track->zb.robj = reloc->robj;
 		track->zb.offset = idx_value;
 		track->zb_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case RADEON_RB3D_COLOROFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
@@ -198,7 +198,7 @@
 		track->cb[0].robj = reloc->robj;
 		track->cb[0].offset = idx_value;
 		track->cb_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case R200_PP_TXOFFSET_0:
 	case R200_PP_TXOFFSET_1:
@@ -215,16 +215,16 @@
 			return r;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= R200_TXO_MACRO_TILE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= R200_TXO_MICRO_TILE;
 
 			tmp = idx_value & ~(0x7 << 2);
 			tmp |= tile_flags;
-			ib[idx] = tmp + ((u32)reloc->lobj.gpu_offset);
+			ib[idx] = tmp + ((u32)reloc->gpu_offset);
 		} else
-			ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+			ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		track->textures[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -268,7 +268,7 @@
 			return r;
 		}
 		track->textures[i].cube_info[face - 1].offset = idx_value;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		track->textures[i].cube_info[face - 1].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -287,9 +287,9 @@
 		}
 
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= RADEON_COLOR_TILE_ENABLE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
 
 			tmp = idx_value & ~(0x7 << 16);
@@ -362,7 +362,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case RADEON_PP_CNTL:
 		{
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 7c63ef8..206caf9 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -640,7 +640,7 @@
 		track->cb[i].robj = reloc->robj;
 		track->cb[i].offset = idx_value;
 		track->cb_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case R300_ZB_DEPTHOFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
@@ -653,7 +653,7 @@
 		track->zb.robj = reloc->robj;
 		track->zb.offset = idx_value;
 		track->zb_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case R300_TX_OFFSET_0:
 	case R300_TX_OFFSET_0+4:
@@ -682,16 +682,16 @@
 
 		if (p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS) {
 			ib[idx] = (idx_value & 31) | /* keep the 1st 5 bits */
-				  ((idx_value & ~31) + (u32)reloc->lobj.gpu_offset);
+				  ((idx_value & ~31) + (u32)reloc->gpu_offset);
 		} else {
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= R300_TXO_MACRO_TILE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= R300_TXO_MICRO_TILE;
-			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+			else if (reloc->tiling_flags & RADEON_TILING_MICRO_SQUARE)
 				tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
 
-			tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
+			tmp = idx_value + ((u32)reloc->gpu_offset);
 			tmp |= tile_flags;
 			ib[idx] = tmp;
 		}
@@ -753,11 +753,11 @@
 				return r;
 			}
 
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= R300_COLOR_TILE_ENABLE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= R300_COLOR_MICROTILE_ENABLE;
-			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+			else if (reloc->tiling_flags & RADEON_TILING_MICRO_SQUARE)
 				tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
 
 			tmp = idx_value & ~(0x7 << 16);
@@ -838,11 +838,11 @@
 				return r;
 			}
 
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			if (reloc->tiling_flags & RADEON_TILING_MACRO)
 				tile_flags |= R300_DEPTHMACROTILE_ENABLE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+			if (reloc->tiling_flags & RADEON_TILING_MICRO)
 				tile_flags |= R300_DEPTHMICROTILE_TILED;
-			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+			else if (reloc->tiling_flags & RADEON_TILING_MICRO_SQUARE)
 				tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
 
 			tmp = idx_value & ~(0x7 << 16);
@@ -1052,7 +1052,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case 0x4e0c:
 		/* RB3D_COLOR_CHANNEL_MASK */
@@ -1097,7 +1097,7 @@
 		track->aa.robj = reloc->robj;
 		track->aa.offset = idx_value;
 		track->aa_dirty = true;
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
 		break;
 	case R300_RB3D_AARESOLVE_PITCH:
 		track->aa.pitch = idx_value & 0x3FFE;
@@ -1162,7 +1162,7 @@
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->lobj.gpu_offset);
+		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->gpu_offset);
 		r = r100_cs_track_check_pkt3_indx_buffer(p, pkt, reloc->robj);
 		if (r) {
 			return r;
@@ -1430,8 +1430,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r300_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 3768aab..802b192 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -325,8 +325,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r420_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index e209eb7..98d6053 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -240,8 +240,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = r520_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 0f4ab92..6e887d0 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2964,7 +2964,8 @@
 	/* post card */
 	atom_asic_init(rdev->mode_info.atom_context);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = r600_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index 47fc2b8..bffac10 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -142,12 +142,15 @@
 }
 
 /* enable the audio stream */
-static void r600_audio_enable(struct radeon_device *rdev,
-			      struct r600_audio_pin *pin,
-			      bool enable)
+void r600_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable)
 {
 	u32 value = 0;
 
+	if (!pin)
+		return;
+
 	if (ASIC_IS_DCE4(rdev)) {
 		if (enable) {
 			value |= 0x81000000; /* Required to enable audio */
@@ -158,7 +161,6 @@
 		WREG32_P(R600_AUDIO_ENABLE,
 			 enable ? 0x81000000 : 0x0, ~0x81000000);
 	}
-	DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
 }
 
 /*
@@ -178,8 +180,8 @@
 	rdev->audio.pin[0].status_bits = 0;
 	rdev->audio.pin[0].category_code = 0;
 	rdev->audio.pin[0].id = 0;
-
-	r600_audio_enable(rdev, &rdev->audio.pin[0], true);
+	/* disable audio.  it will be set up later */
+	r600_audio_enable(rdev, &rdev->audio.pin[0], false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 2812c7d1a..12511bb 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -1022,7 +1022,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SQ_CONFIG:
 		track->sq_config = radeon_get_ib_value(p, idx);
@@ -1043,7 +1043,7 @@
 			track->db_depth_info = radeon_get_ib_value(p, idx);
 			ib[idx] &= C_028010_ARRAY_MODE;
 			track->db_depth_info &= C_028010_ARRAY_MODE;
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+			if (reloc->tiling_flags & RADEON_TILING_MACRO) {
 				ib[idx] |= S_028010_ARRAY_MODE(V_028010_ARRAY_2D_TILED_THIN1);
 				track->db_depth_info |= S_028010_ARRAY_MODE(V_028010_ARRAY_2D_TILED_THIN1);
 			} else {
@@ -1084,9 +1084,9 @@
 		}
 		tmp = (reg - VGT_STRMOUT_BUFFER_BASE_0) / 16;
 		track->vgt_strmout_bo_offset[tmp] = radeon_get_ib_value(p, idx) << 8;
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->vgt_strmout_bo[tmp] = reloc->robj;
-		track->vgt_strmout_bo_mc[tmp] = reloc->lobj.gpu_offset;
+		track->vgt_strmout_bo_mc[tmp] = reloc->gpu_offset;
 		track->streamout_dirty = true;
 		break;
 	case VGT_STRMOUT_BUFFER_SIZE_0:
@@ -1105,7 +1105,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case R_028238_CB_TARGET_MASK:
 		track->cb_target_mask = radeon_get_ib_value(p, idx);
@@ -1142,10 +1142,10 @@
 			}
 			tmp = (reg - R_0280A0_CB_COLOR0_INFO) / 4;
 			track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+			if (reloc->tiling_flags & RADEON_TILING_MACRO) {
 				ib[idx] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_2D_TILED_THIN1);
 				track->cb_color_info[tmp] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_2D_TILED_THIN1);
-			} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+			} else if (reloc->tiling_flags & RADEON_TILING_MICRO) {
 				ib[idx] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_1D_TILED_THIN1);
 				track->cb_color_info[tmp] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_1D_TILED_THIN1);
 			}
@@ -1214,7 +1214,7 @@
 			}
 			track->cb_color_frag_bo[tmp] = reloc->robj;
 			track->cb_color_frag_offset[tmp] = (u64)ib[idx] << 8;
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+			ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		}
 		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
 			track->cb_dirty = true;
@@ -1245,7 +1245,7 @@
 			}
 			track->cb_color_tile_bo[tmp] = reloc->robj;
 			track->cb_color_tile_offset[tmp] = (u64)ib[idx] << 8;
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+			ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		}
 		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
 			track->cb_dirty = true;
@@ -1281,10 +1281,10 @@
 		}
 		tmp = (reg - CB_COLOR0_BASE) / 4;
 		track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx) << 8;
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->cb_color_base_last[tmp] = ib[idx];
 		track->cb_color_bo[tmp] = reloc->robj;
-		track->cb_color_bo_mc[tmp] = reloc->lobj.gpu_offset;
+		track->cb_color_bo_mc[tmp] = reloc->gpu_offset;
 		track->cb_dirty = true;
 		break;
 	case DB_DEPTH_BASE:
@@ -1295,9 +1295,9 @@
 			return -EINVAL;
 		}
 		track->db_offset = radeon_get_ib_value(p, idx) << 8;
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->db_bo = reloc->robj;
-		track->db_bo_mc = reloc->lobj.gpu_offset;
+		track->db_bo_mc = reloc->gpu_offset;
 		track->db_dirty = true;
 		break;
 	case DB_HTILE_DATA_BASE:
@@ -1308,7 +1308,7 @@
 			return -EINVAL;
 		}
 		track->htile_offset = radeon_get_ib_value(p, idx) << 8;
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		track->htile_bo = reloc->robj;
 		track->db_dirty = true;
 		break;
@@ -1377,7 +1377,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SX_MEMORY_EXPORT_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
@@ -1386,7 +1386,7 @@
 					"0x%04X\n", reg);
 			return -EINVAL;
 		}
-		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SX_MISC:
 		track->sx_misc_kill_all_prims = (radeon_get_ib_value(p, idx) & 0x1) != 0;
@@ -1672,7 +1672,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         (idx_value & 0xfffffff0) +
 		         ((u64)(tmp & 0xff) << 32);
 
@@ -1713,7 +1713,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         idx_value +
 		         ((u64)(radeon_get_ib_value(p, idx+1) & 0xff) << 32);
 
@@ -1765,7 +1765,7 @@
 				return -EINVAL;
 			}
 
-			offset = reloc->lobj.gpu_offset +
+			offset = reloc->gpu_offset +
 			         (radeon_get_ib_value(p, idx+1) & 0xfffffff0) +
 			         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -1805,7 +1805,7 @@
 			tmp = radeon_get_ib_value(p, idx) +
 				((u64)(radeon_get_ib_value(p, idx+1) & 0xff) << 32);
 
-			offset = reloc->lobj.gpu_offset + tmp;
+			offset = reloc->gpu_offset + tmp;
 
 			if ((tmp + size) > radeon_bo_size(reloc->robj)) {
 				dev_warn(p->dev, "CP DMA src buffer too small (%llu %lu)\n",
@@ -1835,7 +1835,7 @@
 			tmp = radeon_get_ib_value(p, idx+2) +
 				((u64)(radeon_get_ib_value(p, idx+3) & 0xff) << 32);
 
-			offset = reloc->lobj.gpu_offset + tmp;
+			offset = reloc->gpu_offset + tmp;
 
 			if ((tmp + size) > radeon_bo_size(reloc->robj)) {
 				dev_warn(p->dev, "CP DMA dst buffer too small (%llu %lu)\n",
@@ -1861,7 +1861,7 @@
 				DRM_ERROR("bad SURFACE_SYNC\n");
 				return -EINVAL;
 			}
-			ib[idx+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+			ib[idx+2] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		}
 		break;
 	case PACKET3_EVENT_WRITE:
@@ -1877,7 +1877,7 @@
 				DRM_ERROR("bad EVENT_WRITE\n");
 				return -EINVAL;
 			}
-			offset = reloc->lobj.gpu_offset +
+			offset = reloc->gpu_offset +
 			         (radeon_get_ib_value(p, idx+1) & 0xfffffff8) +
 			         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -1899,7 +1899,7 @@
 			return -EINVAL;
 		}
 
-		offset = reloc->lobj.gpu_offset +
+		offset = reloc->gpu_offset +
 		         (radeon_get_ib_value(p, idx+1) & 0xfffffffc) +
 		         ((u64)(radeon_get_ib_value(p, idx+2) & 0xff) << 32);
 
@@ -1964,11 +1964,11 @@
 					DRM_ERROR("bad SET_RESOURCE\n");
 					return -EINVAL;
 				}
-				base_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+				base_offset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 				if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
-					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+					if (reloc->tiling_flags & RADEON_TILING_MACRO)
 						ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
-					else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+					else if (reloc->tiling_flags & RADEON_TILING_MICRO)
 						ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
 				}
 				texture = reloc->robj;
@@ -1978,13 +1978,13 @@
 					DRM_ERROR("bad SET_RESOURCE\n");
 					return -EINVAL;
 				}
-				mip_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+				mip_offset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 				mipmap = reloc->robj;
 				r = r600_check_texture_resource(p,  idx+(i*7)+1,
 								texture, mipmap,
 								base_offset + radeon_get_ib_value(p, idx+1+(i*7)+2),
 								mip_offset + radeon_get_ib_value(p, idx+1+(i*7)+3),
-								reloc->lobj.tiling_flags);
+								reloc->tiling_flags);
 				if (r)
 					return r;
 				ib[idx+1+(i*7)+2] += base_offset;
@@ -2008,7 +2008,7 @@
 					ib[idx+1+(i*7)+1] = radeon_bo_size(reloc->robj) - offset;
 				}
 
-				offset64 = reloc->lobj.gpu_offset + offset;
+				offset64 = reloc->gpu_offset + offset;
 				ib[idx+1+(i*8)+0] = offset64;
 				ib[idx+1+(i*8)+2] = (ib[idx+1+(i*8)+2] & 0xffffff00) |
 						    (upper_32_bits(offset64) & 0xff);
@@ -2118,7 +2118,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			ib[idx+1] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+			ib[idx+1] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		}
 		break;
 	case PACKET3_SURFACE_BASE_UPDATE:
@@ -2151,7 +2151,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+1] = offset;
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		}
@@ -2170,7 +2170,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+3] = offset;
 			ib[idx+4] = upper_32_bits(offset) & 0xff;
 		}
@@ -2199,7 +2199,7 @@
 				  offset + 8, radeon_bo_size(reloc->robj));
 			return -EINVAL;
 		}
-		offset += reloc->lobj.gpu_offset;
+		offset += reloc->gpu_offset;
 		ib[idx+0] = offset;
 		ib[idx+1] = upper_32_bits(offset) & 0xff;
 		break;
@@ -2224,7 +2224,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+1] = offset;
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		} else {
@@ -2248,7 +2248,7 @@
 					  offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
-			offset += reloc->lobj.gpu_offset;
+			offset += reloc->gpu_offset;
 			ib[idx+3] = offset;
 			ib[idx+4] = upper_32_bits(offset) & 0xff;
 		} else {
@@ -2505,14 +2505,14 @@
 				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset <<= 8;
 
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				p->idx += count + 5;
 			} else {
 				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 
-				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+				ib[idx+2] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 				p->idx += count + 3;
 			}
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
@@ -2539,22 +2539,22 @@
 					/* tiled src, linear dst */
 					src_offset = radeon_get_ib_value(p, idx+1);
 					src_offset <<= 8;
-					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8);
 
 					dst_offset = radeon_get_ib_value(p, idx+5);
 					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
-					ib[idx+5] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+6] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+5] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+6] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
 				} else {
 					/* linear src, tiled dst */
 					src_offset = radeon_get_ib_value(p, idx+5);
 					src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
-					ib[idx+5] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+5] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+6] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 
 					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset <<= 8;
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
+					ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				}
 				p->idx += 7;
 			} else {
@@ -2564,10 +2564,10 @@
 					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+3] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
-					ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
+					ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+2] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+3] += upper_32_bits(dst_reloc->gpu_offset) & 0xff;
+					ib[idx+4] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
 					p->idx += 5;
 				} else {
 					src_offset = radeon_get_ib_value(p, idx+2);
@@ -2575,10 +2575,10 @@
 					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff0000)) << 16;
 
-					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
-					ib[idx+3] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
-					ib[idx+3] += (upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff) << 16;
+					ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+2] += (u32)(src_reloc->gpu_offset & 0xfffffffc);
+					ib[idx+3] += upper_32_bits(src_reloc->gpu_offset) & 0xff;
+					ib[idx+3] += (upper_32_bits(dst_reloc->gpu_offset) & 0xff) << 16;
 					p->idx += 4;
 				}
 			}
@@ -2610,8 +2610,8 @@
 					 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
-			ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
-			ib[idx+3] += (upper_32_bits(dst_reloc->lobj.gpu_offset) << 16) & 0x00ff0000;
+			ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
+			ib[idx+3] += (upper_32_bits(dst_reloc->gpu_offset) << 16) & 0x00ff0000;
 			p->idx += 4;
 			break;
 		case DMA_PACKET_NOP:
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 3016fc1..85a2bb2 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -329,9 +329,6 @@
 	u8 *sadb;
 	int sad_count;
 
-	/* XXX: setting this register causes hangs on some asics */
-	return;
-
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
 		if (connector->encoder == encoder) {
 			radeon_connector = to_radeon_connector(connector);
@@ -460,6 +457,10 @@
 		return;
 	offset = dig->afmt->offset;
 
+	/* disable audio prior to setting up hw */
+	dig->afmt->pin = r600_audio_get_pin(rdev);
+	r600_audio_enable(rdev, dig->afmt->pin, false);
+
 	r600_audio_set_dto(encoder, mode->clock);
 
 	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
@@ -531,6 +532,9 @@
 	WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001);
 
 	r600_hdmi_audio_workaround(encoder);
+
+	/* enable audio after to setting up hw */
+	r600_audio_enable(rdev, dig->afmt->pin, true);
 }
 
 /*
@@ -651,11 +655,6 @@
 	if (!enable && !dig->afmt->enabled)
 		return;
 
-	if (enable)
-		dig->afmt->pin = r600_audio_get_pin(rdev);
-	else
-		dig->afmt->pin = NULL;
-
 	/* Older chipsets require setting HDMI and routing manually */
 	if (!ASIC_IS_DCE3(rdev)) {
 		if (enable)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4581df1..f21db7a 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -363,9 +363,8 @@
 void radeon_fence_process(struct radeon_device *rdev, int ring);
 bool radeon_fence_signaled(struct radeon_fence *fence);
 int radeon_fence_wait(struct radeon_fence *fence, bool interruptible);
-int radeon_fence_wait_locked(struct radeon_fence *fence);
-int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring);
-int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring);
+int radeon_fence_wait_next(struct radeon_device *rdev, int ring);
+int radeon_fence_wait_empty(struct radeon_device *rdev, int ring);
 int radeon_fence_wait_any(struct radeon_device *rdev,
 			  struct radeon_fence **fences,
 			  bool intr);
@@ -457,6 +456,7 @@
 	/* Protected by gem.mutex */
 	struct list_head		list;
 	/* Protected by tbo.reserved */
+	u32				initial_domain;
 	u32				placements[3];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
@@ -479,16 +479,6 @@
 };
 #define gem_to_radeon_bo(gobj) container_of((gobj), struct radeon_bo, gem_base)
 
-struct radeon_bo_list {
-	struct ttm_validate_buffer tv;
-	struct radeon_bo	*bo;
-	uint64_t		gpu_offset;
-	bool			written;
-	unsigned		domain;
-	unsigned		alt_domain;
-	u32			tiling_flags;
-};
-
 int radeon_gem_debugfs_init(struct radeon_device *rdev);
 
 /* sub-allocation manager, it has to be protected by another lock.
@@ -805,8 +795,8 @@
 	unsigned		ring_size;
 	unsigned		ring_free_dw;
 	int			count_dw;
-	unsigned long		last_activity;
-	unsigned		last_rptr;
+	atomic_t		last_rptr;
+	atomic64_t		last_activity;
 	uint64_t		gpu_addr;
 	uint32_t		align_mask;
 	uint32_t		ptr_mask;
@@ -858,17 +848,22 @@
 #define R600_PTE_READABLE	(1 << 5)
 #define R600_PTE_WRITEABLE	(1 << 6)
 
+struct radeon_vm_pt {
+	struct radeon_bo		*bo;
+	uint64_t			addr;
+};
+
 struct radeon_vm {
-	struct list_head		list;
 	struct list_head		va;
 	unsigned			id;
 
 	/* contains the page directory */
-	struct radeon_sa_bo		*page_directory;
+	struct radeon_bo		*page_directory;
 	uint64_t			pd_gpu_addr;
+	unsigned			max_pde_used;
 
 	/* array of page tables, one for each page directory entry */
-	struct radeon_sa_bo		**page_tables;
+	struct radeon_vm_pt		*page_tables;
 
 	struct mutex			mutex;
 	/* last fence for cs using this vm */
@@ -880,10 +875,7 @@
 };
 
 struct radeon_vm_manager {
-	struct mutex			lock;
-	struct list_head		lru_vm;
 	struct radeon_fence		*active[RADEON_NUM_VM];
-	struct radeon_sa_manager	sa_manager;
 	uint32_t			max_pfn;
 	/* number of VMIDs */
 	unsigned			nvm;
@@ -986,9 +978,12 @@
 struct radeon_cs_reloc {
 	struct drm_gem_object		*gobj;
 	struct radeon_bo		*robj;
-	struct radeon_bo_list		lobj;
+	struct ttm_validate_buffer	tv;
+	uint64_t			gpu_offset;
+	unsigned			domain;
+	unsigned			alt_domain;
+	uint32_t			tiling_flags;
 	uint32_t			handle;
-	uint32_t			flags;
 };
 
 struct radeon_cs_chunk {
@@ -1012,6 +1007,7 @@
 	unsigned		nrelocs;
 	struct radeon_cs_reloc	*relocs;
 	struct radeon_cs_reloc	**relocs_ptr;
+	struct radeon_cs_reloc	*vm_bos;
 	struct list_head	validated;
 	unsigned		dma_reloc_idx;
 	/* indices of various chunks */
@@ -1635,7 +1631,6 @@
 
 struct radeon_vce {
 	struct radeon_bo	*vcpu_bo;
-	void			*cpu_addr;
 	uint64_t		gpu_addr;
 	unsigned		fw_version;
 	unsigned		fb_version;
@@ -2117,6 +2112,8 @@
 			      struct drm_file *filp);
 int radeon_gem_va_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
+int radeon_gem_op_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *filp);
 int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
 int radeon_gem_set_tiling_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp);
@@ -2307,6 +2304,10 @@
 	/* virtual memory */
 	struct radeon_vm_manager	vm_manager;
 	struct mutex			gpu_clock_mutex;
+	/* memory stats */
+	atomic64_t			vram_usage;
+	atomic64_t			gtt_usage;
+	atomic64_t			num_bytes_moved;
 	/* ACPI interface */
 	struct radeon_atif		atif;
 	struct radeon_atcs		atcs;
@@ -2794,16 +2795,22 @@
  */
 int radeon_vm_manager_init(struct radeon_device *rdev);
 void radeon_vm_manager_fini(struct radeon_device *rdev);
-void radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm);
+int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm);
 void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm);
-int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm);
-void radeon_vm_add_to_lru(struct radeon_device *rdev, struct radeon_vm *vm);
+struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
+					  struct radeon_vm *vm,
+                                          struct list_head *head);
 struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev,
 				       struct radeon_vm *vm, int ring);
+void radeon_vm_flush(struct radeon_device *rdev,
+                     struct radeon_vm *vm,
+                     int ring);
 void radeon_vm_fence(struct radeon_device *rdev,
 		     struct radeon_vm *vm,
 		     struct radeon_fence *fence);
 uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr);
+int radeon_vm_update_page_directory(struct radeon_device *rdev,
+				    struct radeon_vm *vm);
 int radeon_vm_bo_update(struct radeon_device *rdev,
 			struct radeon_vm *vm,
 			struct radeon_bo *bo,
@@ -2826,6 +2833,12 @@
 void r600_audio_update_hdmi(struct work_struct *work);
 struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev);
 struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev);
+void r600_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable);
+void dce6_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       bool enable);
 
 /*
  * R600 vram scratch functions
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 485848f..fa9a9c0 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -219,7 +219,8 @@
 	memcpy(&output, info->buffer.pointer, size);
 
 	/* TODO: check version? */
-	printk("ATPX version %u\n", output.version);
+	printk("ATPX version %u, functions 0x%08x\n",
+	       output.version, output.function_bits);
 
 	radeon_atpx_parse_functions(&atpx->functions, output.function_bits);
 
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index f28a8d8..2b6e0eb 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -24,16 +24,59 @@
  * Authors:
  *    Jerome Glisse <glisse@freedesktop.org>
  */
+#include <linux/list_sort.h>
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
 #include "radeon_reg.h"
 #include "radeon.h"
 #include "radeon_trace.h"
 
+#define RADEON_CS_MAX_PRIORITY		32u
+#define RADEON_CS_NUM_BUCKETS		(RADEON_CS_MAX_PRIORITY + 1)
+
+/* This is based on the bucket sort with O(n) time complexity.
+ * An item with priority "i" is added to bucket[i]. The lists are then
+ * concatenated in descending order.
+ */
+struct radeon_cs_buckets {
+	struct list_head bucket[RADEON_CS_NUM_BUCKETS];
+};
+
+static void radeon_cs_buckets_init(struct radeon_cs_buckets *b)
+{
+	unsigned i;
+
+	for (i = 0; i < RADEON_CS_NUM_BUCKETS; i++)
+		INIT_LIST_HEAD(&b->bucket[i]);
+}
+
+static void radeon_cs_buckets_add(struct radeon_cs_buckets *b,
+				  struct list_head *item, unsigned priority)
+{
+	/* Since buffers which appear sooner in the relocation list are
+	 * likely to be used more often than buffers which appear later
+	 * in the list, the sort mustn't change the ordering of buffers
+	 * with the same priority, i.e. it must be stable.
+	 */
+	list_add_tail(item, &b->bucket[min(priority, RADEON_CS_MAX_PRIORITY)]);
+}
+
+static void radeon_cs_buckets_get_list(struct radeon_cs_buckets *b,
+				       struct list_head *out_list)
+{
+	unsigned i;
+
+	/* Connect the sorted buckets in the output list. */
+	for (i = 0; i < RADEON_CS_NUM_BUCKETS; i++) {
+		list_splice(&b->bucket[i], out_list);
+	}
+}
+
 static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 {
 	struct drm_device *ddev = p->rdev->ddev;
 	struct radeon_cs_chunk *chunk;
+	struct radeon_cs_buckets buckets;
 	unsigned i, j;
 	bool duplicate;
 
@@ -52,8 +95,12 @@
 	if (p->relocs == NULL) {
 		return -ENOMEM;
 	}
+
+	radeon_cs_buckets_init(&buckets);
+
 	for (i = 0; i < p->nrelocs; i++) {
 		struct drm_radeon_cs_reloc *r;
+		unsigned priority;
 
 		duplicate = false;
 		r = (struct drm_radeon_cs_reloc *)&chunk->kdata[i*4];
@@ -78,8 +125,14 @@
 		}
 		p->relocs_ptr[i] = &p->relocs[i];
 		p->relocs[i].robj = gem_to_radeon_bo(p->relocs[i].gobj);
-		p->relocs[i].lobj.bo = p->relocs[i].robj;
-		p->relocs[i].lobj.written = !!r->write_domain;
+
+		/* The userspace buffer priorities are from 0 to 15. A higher
+		 * number means the buffer is more important.
+		 * Also, the buffers used for write have a higher priority than
+		 * the buffers used for read only, which doubles the range
+		 * to 0 to 31. 32 is reserved for the kernel driver.
+		 */
+		priority = (r->flags & 0xf) * 2 + !!r->write_domain;
 
 		/* the first reloc of an UVD job is the msg and that must be in
 		   VRAM, also but everything into VRAM on AGP cards to avoid
@@ -87,29 +140,38 @@
 		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
 		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
 			/* TODO: is this still needed for NI+ ? */
-			p->relocs[i].lobj.domain =
+			p->relocs[i].domain =
 				RADEON_GEM_DOMAIN_VRAM;
 
-			p->relocs[i].lobj.alt_domain =
+			p->relocs[i].alt_domain =
 				RADEON_GEM_DOMAIN_VRAM;
 
+			/* prioritize this over any other relocation */
+			priority = RADEON_CS_MAX_PRIORITY;
 		} else {
 			uint32_t domain = r->write_domain ?
 				r->write_domain : r->read_domains;
 
-			p->relocs[i].lobj.domain = domain;
+			p->relocs[i].domain = domain;
 			if (domain == RADEON_GEM_DOMAIN_VRAM)
 				domain |= RADEON_GEM_DOMAIN_GTT;
-			p->relocs[i].lobj.alt_domain = domain;
+			p->relocs[i].alt_domain = domain;
 		}
 
-		p->relocs[i].lobj.tv.bo = &p->relocs[i].robj->tbo;
+		p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
 		p->relocs[i].handle = r->handle;
 
-		radeon_bo_list_add_object(&p->relocs[i].lobj,
-					  &p->validated);
+		radeon_cs_buckets_add(&buckets, &p->relocs[i].tv.head,
+				      priority);
 	}
-	return radeon_bo_list_validate(&p->ticket, &p->validated, p->ring);
+
+	radeon_cs_buckets_get_list(&buckets, &p->validated);
+
+	if (p->cs_flags & RADEON_CS_USE_VM)
+		p->vm_bos = radeon_vm_get_bos(p->rdev, p->ib.vm,
+					      &p->validated);
+
+	return radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
 }
 
 static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority)
@@ -290,6 +352,16 @@
 	return 0;
 }
 
+static int cmp_size_smaller_first(void *priv, struct list_head *a,
+				  struct list_head *b)
+{
+	struct radeon_cs_reloc *la = list_entry(a, struct radeon_cs_reloc, tv.head);
+	struct radeon_cs_reloc *lb = list_entry(b, struct radeon_cs_reloc, tv.head);
+
+	/* Sort A before B if A is smaller. */
+	return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages;
+}
+
 /**
  * cs_parser_fini() - clean parser states
  * @parser:	parser structure holding parsing context.
@@ -303,6 +375,18 @@
 	unsigned i;
 
 	if (!error) {
+		/* Sort the buffer list from the smallest to largest buffer,
+		 * which affects the order of buffers in the LRU list.
+		 * This assures that the smallest buffers are added first
+		 * to the LRU list, so they are likely to be later evicted
+		 * first, instead of large buffers whose eviction is more
+		 * expensive.
+		 *
+		 * This slightly lowers the number of bytes moved by TTM
+		 * per frame under memory pressure.
+		 */
+		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
+
 		ttm_eu_fence_buffer_objects(&parser->ticket,
 					    &parser->validated,
 					    parser->ib.fence);
@@ -320,6 +404,7 @@
 	kfree(parser->track);
 	kfree(parser->relocs);
 	kfree(parser->relocs_ptr);
+	kfree(parser->vm_bos);
 	for (i = 0; i < parser->nchunks; i++)
 		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
@@ -359,24 +444,32 @@
 	return r;
 }
 
-static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
+static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p,
 				   struct radeon_vm *vm)
 {
-	struct radeon_device *rdev = parser->rdev;
-	struct radeon_bo_list *lobj;
-	struct radeon_bo *bo;
-	int r;
+	struct radeon_device *rdev = p->rdev;
+	int i, r;
 
-	r = radeon_vm_bo_update(rdev, vm, rdev->ring_tmp_bo.bo, &rdev->ring_tmp_bo.bo->tbo.mem);
-	if (r) {
+	r = radeon_vm_update_page_directory(rdev, vm);
+	if (r)
 		return r;
-	}
-	list_for_each_entry(lobj, &parser->validated, tv.head) {
-		bo = lobj->bo;
-		r = radeon_vm_bo_update(parser->rdev, vm, bo, &bo->tbo.mem);
-		if (r) {
+
+	r = radeon_vm_bo_update(rdev, vm, rdev->ring_tmp_bo.bo,
+				&rdev->ring_tmp_bo.bo->tbo.mem);
+	if (r)
+		return r;
+
+	for (i = 0; i < p->nrelocs; i++) {
+		struct radeon_bo *bo;
+
+		/* ignore duplicates */
+		if (p->relocs_ptr[i] != &p->relocs[i])
+			continue;
+
+		bo = p->relocs[i].robj;
+		r = radeon_vm_bo_update(rdev, vm, bo, &bo->tbo.mem);
+		if (r)
 			return r;
-		}
 	}
 	return 0;
 }
@@ -408,20 +501,13 @@
 	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
 		radeon_uvd_note_usage(rdev);
 
-	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
-	r = radeon_vm_alloc_pt(rdev, vm);
-	if (r) {
-		goto out;
-	}
 	r = radeon_bo_vm_update_pte(parser, vm);
 	if (r) {
 		goto out;
 	}
 	radeon_cs_sync_rings(parser);
 	radeon_semaphore_sync_to(parser->ib.semaphore, vm->fence);
-	radeon_semaphore_sync_to(parser->ib.semaphore,
-				 radeon_vm_grab_id(rdev, vm, parser->ring));
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
@@ -430,14 +516,8 @@
 		r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	}
 
-	if (!r) {
-		radeon_vm_fence(rdev, vm, parser->ib.fence);
-	}
-
 out:
-	radeon_vm_add_to_lru(rdev, vm);
 	mutex_unlock(&vm->mutex);
-	mutex_unlock(&rdev->vm_manager.lock);
 	return r;
 }
 
@@ -705,9 +785,9 @@
 	/* FIXME: we assume reloc size is 4 dwords */
 	if (nomm) {
 		*cs_reloc = p->relocs;
-		(*cs_reloc)->lobj.gpu_offset =
+		(*cs_reloc)->gpu_offset =
 			(u64)relocs_chunk->kdata[idx + 3] << 32;
-		(*cs_reloc)->lobj.gpu_offset |= relocs_chunk->kdata[idx + 0];
+		(*cs_reloc)->gpu_offset |= relocs_chunk->kdata[idx + 0];
 	} else
 		*cs_reloc = p->relocs_ptr[(idx / 4)];
 	return 0;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b012cbb..2e72dcd 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1191,14 +1191,12 @@
 	r = radeon_gem_init(rdev);
 	if (r)
 		return r;
-	/* initialize vm here */
-	mutex_init(&rdev->vm_manager.lock);
+
 	/* Adjust VM size here.
 	 * Currently set to 4GB ((1 << 20) 4k pages).
 	 * Max GPUVM size for cayman and SI is 40 bits.
 	 */
 	rdev->vm_manager.max_pfn = 1 << 20;
-	INIT_LIST_HEAD(&rdev->vm_manager.lru_vm);
 
 	/* Set asic functions */
 	r = radeon_asic_init(rdev);
@@ -1445,10 +1443,9 @@
 	/* evict vram memory */
 	radeon_bo_evict_vram(rdev);
 
-	mutex_lock(&rdev->ring_lock);
 	/* wait for gpu to finish processing current batch */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
-		r = radeon_fence_wait_empty_locked(rdev, i);
+		r = radeon_fence_wait_empty(rdev, i);
 		if (r) {
 			/* delay GPU reset to resume */
 			force_completion = true;
@@ -1457,7 +1454,6 @@
 	if (force_completion) {
 		radeon_fence_driver_force_completion(rdev);
 	}
-	mutex_unlock(&rdev->ring_lock);
 
 	radeon_save_bios_scratch_regs(rdev);
 
@@ -1521,13 +1517,16 @@
 	if (r)
 		DRM_ERROR("ib ring test failed (%d).\n", r);
 
-	if (rdev->pm.dpm_enabled) {
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
 		/* do dpm late init */
 		r = radeon_pm_late_init(rdev);
 		if (r) {
 			rdev->pm.dpm_enabled = false;
 			DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n");
 		}
+	} else {
+		/* resume old pm late */
+		radeon_pm_resume(rdev);
 	}
 
 	radeon_restore_bios_scratch_regs(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 84a1bbb7..4392b7c 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -79,9 +79,10 @@
  *   2.35.0 - Add CIK macrotile mode array query
  *   2.36.0 - Fix CIK DCE tiling setup
  *   2.37.0 - allow GS ring setup on r6xx/r7xx
+ *   2.38.0 - RADEON_GEM_OP (GET_INITIAL_DOMAIN, SET_INITIAL_DOMAIN)
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	37
+#define KMS_DRIVER_MINOR	38
 #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_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index c37cb79..a77b1c1 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -288,7 +288,6 @@
  * @rdev: radeon device pointer
  * @target_seq: sequence number(s) we want to wait for
  * @intr: use interruptable sleep
- * @lock_ring: whether the ring should be locked or not
  *
  * Wait for the requested sequence number(s) to be written by any ring
  * (all asics).  Sequnce number array is indexed by ring id.
@@ -299,7 +298,7 @@
  * -EDEADLK is returned when a GPU lockup has been detected.
  */
 static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 *target_seq,
-				 bool intr, bool lock_ring)
+				 bool intr)
 {
 	uint64_t last_seq[RADEON_NUM_RINGS];
 	bool signaled;
@@ -358,9 +357,6 @@
 			if (i != RADEON_NUM_RINGS)
 				continue;
 
-			if (lock_ring)
-				mutex_lock(&rdev->ring_lock);
-
 			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
 				if (!target_seq[i])
 					continue;
@@ -378,14 +374,9 @@
 
 				/* remember that we need an reset */
 				rdev->needs_reset = true;
-				if (lock_ring)
-					mutex_unlock(&rdev->ring_lock);
 				wake_up_all(&rdev->fence_queue);
 				return -EDEADLK;
 			}
-
-			if (lock_ring)
-				mutex_unlock(&rdev->ring_lock);
 		}
 	}
 	return 0;
@@ -416,7 +407,7 @@
 	if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
 		return 0;
 
-	r = radeon_fence_wait_seq(fence->rdev, seq, intr, true);
+	r = radeon_fence_wait_seq(fence->rdev, seq, intr);
 	if (r)
 		return r;
 
@@ -464,7 +455,7 @@
 	if (num_rings == 0)
 		return -ENOENT;
 
-	r = radeon_fence_wait_seq(rdev, seq, intr, true);
+	r = radeon_fence_wait_seq(rdev, seq, intr);
 	if (r) {
 		return r;
 	}
@@ -472,37 +463,7 @@
 }
 
 /**
- * radeon_fence_wait_locked - wait for a fence to signal
- *
- * @fence: radeon fence object
- *
- * Wait for the requested fence to signal (all asics).
- * Returns 0 if the fence has passed, error for all other cases.
- */
-int radeon_fence_wait_locked(struct radeon_fence *fence)
-{
-	uint64_t seq[RADEON_NUM_RINGS] = {};
-	int r;
-
-	if (fence == NULL) {
-		WARN(1, "Querying an invalid fence : %p !\n", fence);
-		return -EINVAL;
-	}
-
-	seq[fence->ring] = fence->seq;
-	if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
-		return 0;
-
-	r = radeon_fence_wait_seq(fence->rdev, seq, false, false);
-	if (r)
-		return r;
-
-	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
-	return 0;
-}
-
-/**
- * radeon_fence_wait_next_locked - wait for the next fence to signal
+ * radeon_fence_wait_next - wait for the next fence to signal
  *
  * @rdev: radeon device pointer
  * @ring: ring index the fence is associated with
@@ -511,7 +472,7 @@
  * Returns 0 if the next fence has passed, error for all other cases.
  * Caller must hold ring lock.
  */
-int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring)
+int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 {
 	uint64_t seq[RADEON_NUM_RINGS] = {};
 
@@ -521,11 +482,11 @@
 		   already the last emited fence */
 		return -ENOENT;
 	}
-	return radeon_fence_wait_seq(rdev, seq, false, false);
+	return radeon_fence_wait_seq(rdev, seq, false);
 }
 
 /**
- * radeon_fence_wait_empty_locked - wait for all fences to signal
+ * radeon_fence_wait_empty - wait for all fences to signal
  *
  * @rdev: radeon device pointer
  * @ring: ring index the fence is associated with
@@ -534,7 +495,7 @@
  * Returns 0 if the fences have passed, error for all other cases.
  * Caller must hold ring lock.
  */
-int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring)
+int radeon_fence_wait_empty(struct radeon_device *rdev, int ring)
 {
 	uint64_t seq[RADEON_NUM_RINGS] = {};
 	int r;
@@ -543,7 +504,7 @@
 	if (!seq[ring])
 		return 0;
 
-	r = radeon_fence_wait_seq(rdev, seq, false, false);
+	r = radeon_fence_wait_seq(rdev, seq, false);
 	if (r) {
 		if (r == -EDEADLK)
 			return -EDEADLK;
@@ -794,7 +755,7 @@
 	for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
 		if (!rdev->fence_drv[ring].initialized)
 			continue;
-		r = radeon_fence_wait_empty_locked(rdev, ring);
+		r = radeon_fence_wait_empty(rdev, ring);
 		if (r) {
 			/* no need to trigger GPU reset as we are unloading */
 			radeon_fence_driver_force_completion(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index a8f9b46..2e72365 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -28,8 +28,6 @@
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
 #include "radeon.h"
-#include "radeon_reg.h"
-#include "radeon_trace.h"
 
 /*
  * GART
@@ -394,959 +392,3 @@
 
 	radeon_dummy_page_fini(rdev);
 }
-
-/*
- * GPUVM
- * GPUVM is similar to the legacy gart on older asics, however
- * rather than there being a single global gart table
- * for the entire GPU, there are multiple VM page tables active
- * at any given time.  The VM page tables can contain a mix
- * vram pages and system memory pages and system memory pages
- * can be mapped as snooped (cached system pages) or unsnooped
- * (uncached system pages).
- * Each VM has an ID associated with it and there is a page table
- * associated with each VMID.  When execting a command buffer,
- * the kernel tells the the ring what VMID to use for that command
- * buffer.  VMIDs are allocated dynamically as commands are submitted.
- * The userspace drivers maintain their own address space and the kernel
- * sets up their pages tables accordingly when they submit their
- * command buffers and a VMID is assigned.
- * Cayman/Trinity support up to 8 active VMs at any given time;
- * SI supports 16.
- */
-
-/*
- * vm helpers
- *
- * TODO bind a default page at vm initialization for default address
- */
-
-/**
- * radeon_vm_num_pde - return the number of page directory entries
- *
- * @rdev: radeon_device pointer
- *
- * Calculate the number of page directory entries (cayman+).
- */
-static unsigned radeon_vm_num_pdes(struct radeon_device *rdev)
-{
-	return rdev->vm_manager.max_pfn >> RADEON_VM_BLOCK_SIZE;
-}
-
-/**
- * radeon_vm_directory_size - returns the size of the page directory in bytes
- *
- * @rdev: radeon_device pointer
- *
- * Calculate the size of the page directory in bytes (cayman+).
- */
-static unsigned radeon_vm_directory_size(struct radeon_device *rdev)
-{
-	return RADEON_GPU_PAGE_ALIGN(radeon_vm_num_pdes(rdev) * 8);
-}
-
-/**
- * radeon_vm_manager_init - init the vm manager
- *
- * @rdev: radeon_device pointer
- *
- * Init the vm manager (cayman+).
- * Returns 0 for success, error for failure.
- */
-int radeon_vm_manager_init(struct radeon_device *rdev)
-{
-	struct radeon_vm *vm;
-	struct radeon_bo_va *bo_va;
-	int r;
-	unsigned size;
-
-	if (!rdev->vm_manager.enabled) {
-		/* allocate enough for 2 full VM pts */
-		size = radeon_vm_directory_size(rdev);
-		size += rdev->vm_manager.max_pfn * 8;
-		size *= 2;
-		r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
-					      RADEON_GPU_PAGE_ALIGN(size),
-					      RADEON_VM_PTB_ALIGN_SIZE,
-					      RADEON_GEM_DOMAIN_VRAM);
-		if (r) {
-			dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n",
-				(rdev->vm_manager.max_pfn * 8) >> 10);
-			return r;
-		}
-
-		r = radeon_asic_vm_init(rdev);
-		if (r)
-			return r;
-
-		rdev->vm_manager.enabled = true;
-
-		r = radeon_sa_bo_manager_start(rdev, &rdev->vm_manager.sa_manager);
-		if (r)
-			return r;
-	}
-
-	/* restore page table */
-	list_for_each_entry(vm, &rdev->vm_manager.lru_vm, list) {
-		if (vm->page_directory == NULL)
-			continue;
-
-		list_for_each_entry(bo_va, &vm->va, vm_list) {
-			bo_va->valid = false;
-		}
-	}
-	return 0;
-}
-
-/**
- * radeon_vm_free_pt - free the page table for a specific vm
- *
- * @rdev: radeon_device pointer
- * @vm: vm to unbind
- *
- * Free the page table of a specific vm (cayman+).
- *
- * Global and local mutex must be lock!
- */
-static void radeon_vm_free_pt(struct radeon_device *rdev,
-				    struct radeon_vm *vm)
-{
-	struct radeon_bo_va *bo_va;
-	int i;
-
-	if (!vm->page_directory)
-		return;
-
-	list_del_init(&vm->list);
-	radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
-
-	list_for_each_entry(bo_va, &vm->va, vm_list) {
-		bo_va->valid = false;
-	}
-
-	if (vm->page_tables == NULL)
-		return;
-
-	for (i = 0; i < radeon_vm_num_pdes(rdev); i++)
-		radeon_sa_bo_free(rdev, &vm->page_tables[i], vm->fence);
-
-	kfree(vm->page_tables);
-}
-
-/**
- * radeon_vm_manager_fini - tear down the vm manager
- *
- * @rdev: radeon_device pointer
- *
- * Tear down the VM manager (cayman+).
- */
-void radeon_vm_manager_fini(struct radeon_device *rdev)
-{
-	struct radeon_vm *vm, *tmp;
-	int i;
-
-	if (!rdev->vm_manager.enabled)
-		return;
-
-	mutex_lock(&rdev->vm_manager.lock);
-	/* free all allocated page tables */
-	list_for_each_entry_safe(vm, tmp, &rdev->vm_manager.lru_vm, list) {
-		mutex_lock(&vm->mutex);
-		radeon_vm_free_pt(rdev, vm);
-		mutex_unlock(&vm->mutex);
-	}
-	for (i = 0; i < RADEON_NUM_VM; ++i) {
-		radeon_fence_unref(&rdev->vm_manager.active[i]);
-	}
-	radeon_asic_vm_fini(rdev);
-	mutex_unlock(&rdev->vm_manager.lock);
-
-	radeon_sa_bo_manager_suspend(rdev, &rdev->vm_manager.sa_manager);
-	radeon_sa_bo_manager_fini(rdev, &rdev->vm_manager.sa_manager);
-	rdev->vm_manager.enabled = false;
-}
-
-/**
- * radeon_vm_evict - evict page table to make room for new one
- *
- * @rdev: radeon_device pointer
- * @vm: VM we want to allocate something for
- *
- * Evict a VM from the lru, making sure that it isn't @vm. (cayman+).
- * Returns 0 for success, -ENOMEM for failure.
- *
- * Global and local mutex must be locked!
- */
-static int radeon_vm_evict(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	struct radeon_vm *vm_evict;
-
-	if (list_empty(&rdev->vm_manager.lru_vm))
-		return -ENOMEM;
-
-	vm_evict = list_first_entry(&rdev->vm_manager.lru_vm,
-				    struct radeon_vm, list);
-	if (vm_evict == vm)
-		return -ENOMEM;
-
-	mutex_lock(&vm_evict->mutex);
-	radeon_vm_free_pt(rdev, vm_evict);
-	mutex_unlock(&vm_evict->mutex);
-	return 0;
-}
-
-/**
- * radeon_vm_alloc_pt - allocates a page table for a VM
- *
- * @rdev: radeon_device pointer
- * @vm: vm to bind
- *
- * Allocate a page table for the requested vm (cayman+).
- * Returns 0 for success, error for failure.
- *
- * Global and local mutex must be locked!
- */
-int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	unsigned pd_size, pd_entries, pts_size;
-	struct radeon_ib ib;
-	int r;
-
-	if (vm == NULL) {
-		return -EINVAL;
-	}
-
-	if (vm->page_directory != NULL) {
-		return 0;
-	}
-
-	pd_size = radeon_vm_directory_size(rdev);
-	pd_entries = radeon_vm_num_pdes(rdev);
-
-retry:
-	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
-			     &vm->page_directory, pd_size,
-			     RADEON_VM_PTB_ALIGN_SIZE, false);
-	if (r == -ENOMEM) {
-		r = radeon_vm_evict(rdev, vm);
-		if (r)
-			return r;
-		goto retry;
-
-	} else if (r) {
-		return r;
-	}
-
-	vm->pd_gpu_addr = radeon_sa_bo_gpu_addr(vm->page_directory);
-
-	/* Initially clear the page directory */
-	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib,
-			  NULL, pd_entries * 2 + 64);
-	if (r) {
-		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
-		return r;
-	}
-
-	ib.length_dw = 0;
-
-	radeon_asic_vm_set_page(rdev, &ib, vm->pd_gpu_addr,
-				0, pd_entries, 0, 0);
-
-	radeon_semaphore_sync_to(ib.semaphore, vm->fence);
-	r = radeon_ib_schedule(rdev, &ib, NULL);
-	if (r) {
-		radeon_ib_free(rdev, &ib);
-		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
-		return r;
-	}
-	radeon_fence_unref(&vm->fence);
-	vm->fence = radeon_fence_ref(ib.fence);
-	radeon_ib_free(rdev, &ib);
-	radeon_fence_unref(&vm->last_flush);
-
-	/* allocate page table array */
-	pts_size = radeon_vm_num_pdes(rdev) * sizeof(struct radeon_sa_bo *);
-	vm->page_tables = kzalloc(pts_size, GFP_KERNEL);
-
-	if (vm->page_tables == NULL) {
-		DRM_ERROR("Cannot allocate memory for page table array\n");
-		radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-/**
- * radeon_vm_add_to_lru - add VMs page table to LRU list
- *
- * @rdev: radeon_device pointer
- * @vm: vm to add to LRU
- *
- * Add the allocated page table to the LRU list (cayman+).
- *
- * Global mutex must be locked!
- */
-void radeon_vm_add_to_lru(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	list_del_init(&vm->list);
-	list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
-}
-
-/**
- * radeon_vm_grab_id - allocate the next free VMID
- *
- * @rdev: radeon_device pointer
- * @vm: vm to allocate id for
- * @ring: ring we want to submit job to
- *
- * Allocate an id for the vm (cayman+).
- * Returns the fence we need to sync to (if any).
- *
- * Global and local mutex must be locked!
- */
-struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev,
-				       struct radeon_vm *vm, int ring)
-{
-	struct radeon_fence *best[RADEON_NUM_RINGS] = {};
-	unsigned choices[2] = {};
-	unsigned i;
-
-	/* check if the id is still valid */
-	if (vm->last_id_use && vm->last_id_use == rdev->vm_manager.active[vm->id])
-		return NULL;
-
-	/* we definately need to flush */
-	radeon_fence_unref(&vm->last_flush);
-
-	/* skip over VMID 0, since it is the system VM */
-	for (i = 1; i < rdev->vm_manager.nvm; ++i) {
-		struct radeon_fence *fence = rdev->vm_manager.active[i];
-
-		if (fence == NULL) {
-			/* found a free one */
-			vm->id = i;
-			trace_radeon_vm_grab_id(vm->id, ring);
-			return NULL;
-		}
-
-		if (radeon_fence_is_earlier(fence, best[fence->ring])) {
-			best[fence->ring] = fence;
-			choices[fence->ring == ring ? 0 : 1] = i;
-		}
-	}
-
-	for (i = 0; i < 2; ++i) {
-		if (choices[i]) {
-			vm->id = choices[i];
-			trace_radeon_vm_grab_id(vm->id, ring);
-			return rdev->vm_manager.active[choices[i]];
-		}
-	}
-
-	/* should never happen */
-	BUG();
-	return NULL;
-}
-
-/**
- * radeon_vm_fence - remember fence for vm
- *
- * @rdev: radeon_device pointer
- * @vm: vm we want to fence
- * @fence: fence to remember
- *
- * Fence the vm (cayman+).
- * Set the fence used to protect page table and id.
- *
- * Global and local mutex must be locked!
- */
-void radeon_vm_fence(struct radeon_device *rdev,
-		     struct radeon_vm *vm,
-		     struct radeon_fence *fence)
-{
-	radeon_fence_unref(&rdev->vm_manager.active[vm->id]);
-	rdev->vm_manager.active[vm->id] = radeon_fence_ref(fence);
-
-	radeon_fence_unref(&vm->fence);
-	vm->fence = radeon_fence_ref(fence);
-
-	radeon_fence_unref(&vm->last_id_use);
-	vm->last_id_use = radeon_fence_ref(fence);
-}
-
-/**
- * radeon_vm_bo_find - find the bo_va for a specific vm & bo
- *
- * @vm: requested vm
- * @bo: requested buffer object
- *
- * Find @bo inside the requested vm (cayman+).
- * Search inside the @bos vm list for the requested vm
- * Returns the found bo_va or NULL if none is found
- *
- * Object has to be reserved!
- */
-struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
-				       struct radeon_bo *bo)
-{
-	struct radeon_bo_va *bo_va;
-
-	list_for_each_entry(bo_va, &bo->va, bo_list) {
-		if (bo_va->vm == vm) {
-			return bo_va;
-		}
-	}
-	return NULL;
-}
-
-/**
- * radeon_vm_bo_add - add a bo to a specific vm
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- * @bo: radeon buffer object
- *
- * Add @bo into the requested vm (cayman+).
- * Add @bo to the list of bos associated with the vm
- * Returns newly added bo_va or NULL for failure
- *
- * Object has to be reserved!
- */
-struct radeon_bo_va *radeon_vm_bo_add(struct radeon_device *rdev,
-				      struct radeon_vm *vm,
-				      struct radeon_bo *bo)
-{
-	struct radeon_bo_va *bo_va;
-
-	bo_va = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
-	if (bo_va == NULL) {
-		return NULL;
-	}
-	bo_va->vm = vm;
-	bo_va->bo = bo;
-	bo_va->soffset = 0;
-	bo_va->eoffset = 0;
-	bo_va->flags = 0;
-	bo_va->valid = false;
-	bo_va->ref_count = 1;
-	INIT_LIST_HEAD(&bo_va->bo_list);
-	INIT_LIST_HEAD(&bo_va->vm_list);
-
-	mutex_lock(&vm->mutex);
-	list_add(&bo_va->vm_list, &vm->va);
-	list_add_tail(&bo_va->bo_list, &bo->va);
-	mutex_unlock(&vm->mutex);
-
-	return bo_va;
-}
-
-/**
- * radeon_vm_bo_set_addr - set bos virtual address inside a vm
- *
- * @rdev: radeon_device pointer
- * @bo_va: bo_va to store the address
- * @soffset: requested offset of the buffer in the VM address space
- * @flags: attributes of pages (read/write/valid/etc.)
- *
- * Set offset of @bo_va (cayman+).
- * Validate and set the offset requested within the vm address space.
- * Returns 0 for success, error for failure.
- *
- * Object has to be reserved!
- */
-int radeon_vm_bo_set_addr(struct radeon_device *rdev,
-			  struct radeon_bo_va *bo_va,
-			  uint64_t soffset,
-			  uint32_t flags)
-{
-	uint64_t size = radeon_bo_size(bo_va->bo);
-	uint64_t eoffset, last_offset = 0;
-	struct radeon_vm *vm = bo_va->vm;
-	struct radeon_bo_va *tmp;
-	struct list_head *head;
-	unsigned last_pfn;
-
-	if (soffset) {
-		/* make sure object fit at this offset */
-		eoffset = soffset + size;
-		if (soffset >= eoffset) {
-			return -EINVAL;
-		}
-
-		last_pfn = eoffset / RADEON_GPU_PAGE_SIZE;
-		if (last_pfn > rdev->vm_manager.max_pfn) {
-			dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n",
-				last_pfn, rdev->vm_manager.max_pfn);
-			return -EINVAL;
-		}
-
-	} else {
-		eoffset = last_pfn = 0;
-	}
-
-	mutex_lock(&vm->mutex);
-	head = &vm->va;
-	last_offset = 0;
-	list_for_each_entry(tmp, &vm->va, vm_list) {
-		if (bo_va == tmp) {
-			/* skip over currently modified bo */
-			continue;
-		}
-
-		if (soffset >= last_offset && eoffset <= tmp->soffset) {
-			/* bo can be added before this one */
-			break;
-		}
-		if (eoffset > tmp->soffset && soffset < tmp->eoffset) {
-			/* bo and tmp overlap, invalid offset */
-			dev_err(rdev->dev, "bo %p va 0x%08X conflict with (bo %p 0x%08X 0x%08X)\n",
-				bo_va->bo, (unsigned)bo_va->soffset, tmp->bo,
-				(unsigned)tmp->soffset, (unsigned)tmp->eoffset);
-			mutex_unlock(&vm->mutex);
-			return -EINVAL;
-		}
-		last_offset = tmp->eoffset;
-		head = &tmp->vm_list;
-	}
-
-	bo_va->soffset = soffset;
-	bo_va->eoffset = eoffset;
-	bo_va->flags = flags;
-	bo_va->valid = false;
-	list_move(&bo_va->vm_list, head);
-
-	mutex_unlock(&vm->mutex);
-	return 0;
-}
-
-/**
- * radeon_vm_map_gart - get the physical address of a gart page
- *
- * @rdev: radeon_device pointer
- * @addr: the unmapped addr
- *
- * Look up the physical address of the page that the pte resolves
- * to (cayman+).
- * Returns the physical address of the page.
- */
-uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr)
-{
-	uint64_t result;
-
-	/* page table offset */
-	result = rdev->gart.pages_addr[addr >> PAGE_SHIFT];
-
-	/* in case cpu page size != gpu page size*/
-	result |= addr & (~PAGE_MASK);
-
-	return result;
-}
-
-/**
- * radeon_vm_page_flags - translate page flags to what the hw uses
- *
- * @flags: flags comming from userspace
- *
- * Translate the flags the userspace ABI uses to hw flags.
- */
-static uint32_t radeon_vm_page_flags(uint32_t flags)
-{
-        uint32_t hw_flags = 0;
-        hw_flags |= (flags & RADEON_VM_PAGE_VALID) ? R600_PTE_VALID : 0;
-        hw_flags |= (flags & RADEON_VM_PAGE_READABLE) ? R600_PTE_READABLE : 0;
-        hw_flags |= (flags & RADEON_VM_PAGE_WRITEABLE) ? R600_PTE_WRITEABLE : 0;
-        if (flags & RADEON_VM_PAGE_SYSTEM) {
-                hw_flags |= R600_PTE_SYSTEM;
-                hw_flags |= (flags & RADEON_VM_PAGE_SNOOPED) ? R600_PTE_SNOOPED : 0;
-        }
-        return hw_flags;
-}
-
-/**
- * radeon_vm_update_pdes - make sure that page directory is valid
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- * @start: start of GPU address range
- * @end: end of GPU address range
- *
- * Allocates new page tables if necessary
- * and updates the page directory (cayman+).
- * Returns 0 for success, error for failure.
- *
- * Global and local mutex must be locked!
- */
-static int radeon_vm_update_pdes(struct radeon_device *rdev,
-				 struct radeon_vm *vm,
-				 struct radeon_ib *ib,
-				 uint64_t start, uint64_t end)
-{
-	static const uint32_t incr = RADEON_VM_PTE_COUNT * 8;
-
-	uint64_t last_pde = ~0, last_pt = ~0;
-	unsigned count = 0;
-	uint64_t pt_idx;
-	int r;
-
-	start = (start / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE;
-	end = (end / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE;
-
-	/* walk over the address space and update the page directory */
-	for (pt_idx = start; pt_idx <= end; ++pt_idx) {
-		uint64_t pde, pt;
-
-		if (vm->page_tables[pt_idx])
-			continue;
-
-retry:
-		r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
-				     &vm->page_tables[pt_idx],
-				     RADEON_VM_PTE_COUNT * 8,
-				     RADEON_GPU_PAGE_SIZE, false);
-
-		if (r == -ENOMEM) {
-			r = radeon_vm_evict(rdev, vm);
-			if (r)
-				return r;
-			goto retry;
-		} else if (r) {
-			return r;
-		}
-
-		pde = vm->pd_gpu_addr + pt_idx * 8;
-
-		pt = radeon_sa_bo_gpu_addr(vm->page_tables[pt_idx]);
-
-		if (((last_pde + 8 * count) != pde) ||
-		    ((last_pt + incr * count) != pt)) {
-
-			if (count) {
-				radeon_asic_vm_set_page(rdev, ib, last_pde,
-							last_pt, count, incr,
-							R600_PTE_VALID);
-
-				count *= RADEON_VM_PTE_COUNT;
-				radeon_asic_vm_set_page(rdev, ib, last_pt, 0,
-							count, 0, 0);
-			}
-
-			count = 1;
-			last_pde = pde;
-			last_pt = pt;
-		} else {
-			++count;
-		}
-	}
-
-	if (count) {
-		radeon_asic_vm_set_page(rdev, ib, last_pde, last_pt, count,
-					incr, R600_PTE_VALID);
-
-		count *= RADEON_VM_PTE_COUNT;
-		radeon_asic_vm_set_page(rdev, ib, last_pt, 0,
-					count, 0, 0);
-	}
-
-	return 0;
-}
-
-/**
- * radeon_vm_update_ptes - make sure that page tables are valid
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- * @start: start of GPU address range
- * @end: end of GPU address range
- * @dst: destination address to map to
- * @flags: mapping flags
- *
- * Update the page tables in the range @start - @end (cayman+).
- *
- * Global and local mutex must be locked!
- */
-static void radeon_vm_update_ptes(struct radeon_device *rdev,
-				  struct radeon_vm *vm,
-				  struct radeon_ib *ib,
-				  uint64_t start, uint64_t end,
-				  uint64_t dst, uint32_t flags)
-{
-	static const uint64_t mask = RADEON_VM_PTE_COUNT - 1;
-
-	uint64_t last_pte = ~0, last_dst = ~0;
-	unsigned count = 0;
-	uint64_t addr;
-
-	start = start / RADEON_GPU_PAGE_SIZE;
-	end = end / RADEON_GPU_PAGE_SIZE;
-
-	/* walk over the address space and update the page tables */
-	for (addr = start; addr < end; ) {
-		uint64_t pt_idx = addr >> RADEON_VM_BLOCK_SIZE;
-		unsigned nptes;
-		uint64_t pte;
-
-		if ((addr & ~mask) == (end & ~mask))
-			nptes = end - addr;
-		else
-			nptes = RADEON_VM_PTE_COUNT - (addr & mask);
-
-		pte = radeon_sa_bo_gpu_addr(vm->page_tables[pt_idx]);
-		pte += (addr & mask) * 8;
-
-		if ((last_pte + 8 * count) != pte) {
-
-			if (count) {
-				radeon_asic_vm_set_page(rdev, ib, last_pte,
-							last_dst, count,
-							RADEON_GPU_PAGE_SIZE,
-							flags);
-			}
-
-			count = nptes;
-			last_pte = pte;
-			last_dst = dst;
-		} else {
-			count += nptes;
-		}
-
-		addr += nptes;
-		dst += nptes * RADEON_GPU_PAGE_SIZE;
-	}
-
-	if (count) {
-		radeon_asic_vm_set_page(rdev, ib, last_pte,
-					last_dst, count,
-					RADEON_GPU_PAGE_SIZE, flags);
-	}
-}
-
-/**
- * radeon_vm_bo_update - map a bo into the vm page table
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- * @bo: radeon buffer object
- * @mem: ttm mem
- *
- * Fill in the page table entries for @bo (cayman+).
- * Returns 0 for success, -EINVAL for failure.
- *
- * Object have to be reserved & global and local mutex must be locked!
- */
-int radeon_vm_bo_update(struct radeon_device *rdev,
-			struct radeon_vm *vm,
-			struct radeon_bo *bo,
-			struct ttm_mem_reg *mem)
-{
-	struct radeon_ib ib;
-	struct radeon_bo_va *bo_va;
-	unsigned nptes, npdes, ndw;
-	uint64_t addr;
-	int r;
-
-	/* nothing to do if vm isn't bound */
-	if (vm->page_directory == NULL)
-		return 0;
-
-	bo_va = radeon_vm_bo_find(vm, bo);
-	if (bo_va == NULL) {
-		dev_err(rdev->dev, "bo %p not in vm %p\n", bo, vm);
-		return -EINVAL;
-	}
-
-	if (!bo_va->soffset) {
-		dev_err(rdev->dev, "bo %p don't has a mapping in vm %p\n",
-			bo, vm);
-		return -EINVAL;
-	}
-
-	if ((bo_va->valid && mem) || (!bo_va->valid && mem == NULL))
-		return 0;
-
-	bo_va->flags &= ~RADEON_VM_PAGE_VALID;
-	bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM;
-	if (mem) {
-		addr = mem->start << PAGE_SHIFT;
-		if (mem->mem_type != TTM_PL_SYSTEM) {
-			bo_va->flags |= RADEON_VM_PAGE_VALID;
-			bo_va->valid = true;
-		}
-		if (mem->mem_type == TTM_PL_TT) {
-			bo_va->flags |= RADEON_VM_PAGE_SYSTEM;
-		} else {
-			addr += rdev->vm_manager.vram_base_offset;
-		}
-	} else {
-		addr = 0;
-		bo_va->valid = false;
-	}
-
-	trace_radeon_vm_bo_update(bo_va);
-
-	nptes = radeon_bo_ngpu_pages(bo);
-
-	/* assume two extra pdes in case the mapping overlaps the borders */
-	npdes = (nptes >> RADEON_VM_BLOCK_SIZE) + 2;
-
-	/* padding, etc. */
-	ndw = 64;
-
-	if (RADEON_VM_BLOCK_SIZE > 11)
-		/* reserve space for one header for every 2k dwords */
-		ndw += (nptes >> 11) * 4;
-	else
-		/* reserve space for one header for
-		    every (1 << BLOCK_SIZE) entries */
-		ndw += (nptes >> RADEON_VM_BLOCK_SIZE) * 4;
-
-	/* reserve space for pte addresses */
-	ndw += nptes * 2;
-
-	/* reserve space for one header for every 2k dwords */
-	ndw += (npdes >> 11) * 4;
-
-	/* reserve space for pde addresses */
-	ndw += npdes * 2;
-
-	/* reserve space for clearing new page tables */
-	ndw += npdes * 2 * RADEON_VM_PTE_COUNT;
-
-	/* update too big for an IB */
-	if (ndw > 0xfffff)
-		return -ENOMEM;
-
-	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib, NULL, ndw * 4);
-	if (r)
-		return r;
-	ib.length_dw = 0;
-
-	r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
-	if (r) {
-		radeon_ib_free(rdev, &ib);
-		return r;
-	}
-
-	radeon_vm_update_ptes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset,
-			      addr, radeon_vm_page_flags(bo_va->flags));
-
-	radeon_semaphore_sync_to(ib.semaphore, vm->fence);
-	r = radeon_ib_schedule(rdev, &ib, NULL);
-	if (r) {
-		radeon_ib_free(rdev, &ib);
-		return r;
-	}
-	radeon_fence_unref(&vm->fence);
-	vm->fence = radeon_fence_ref(ib.fence);
-	radeon_ib_free(rdev, &ib);
-	radeon_fence_unref(&vm->last_flush);
-
-	return 0;
-}
-
-/**
- * radeon_vm_bo_rmv - remove a bo to a specific vm
- *
- * @rdev: radeon_device pointer
- * @bo_va: requested bo_va
- *
- * Remove @bo_va->bo from the requested vm (cayman+).
- * Remove @bo_va->bo from the list of bos associated with the bo_va->vm and
- * remove the ptes for @bo_va in the page table.
- * Returns 0 for success.
- *
- * Object have to be reserved!
- */
-int radeon_vm_bo_rmv(struct radeon_device *rdev,
-		     struct radeon_bo_va *bo_va)
-{
-	int r = 0;
-
-	mutex_lock(&rdev->vm_manager.lock);
-	mutex_lock(&bo_va->vm->mutex);
-	if (bo_va->soffset) {
-		r = radeon_vm_bo_update(rdev, bo_va->vm, bo_va->bo, NULL);
-	}
-	mutex_unlock(&rdev->vm_manager.lock);
-	list_del(&bo_va->vm_list);
-	mutex_unlock(&bo_va->vm->mutex);
-	list_del(&bo_va->bo_list);
-
-	kfree(bo_va);
-	return r;
-}
-
-/**
- * radeon_vm_bo_invalidate - mark the bo as invalid
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- * @bo: radeon buffer object
- *
- * Mark @bo as invalid (cayman+).
- */
-void radeon_vm_bo_invalidate(struct radeon_device *rdev,
-			     struct radeon_bo *bo)
-{
-	struct radeon_bo_va *bo_va;
-
-	list_for_each_entry(bo_va, &bo->va, bo_list) {
-		bo_va->valid = false;
-	}
-}
-
-/**
- * radeon_vm_init - initialize a vm instance
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- *
- * Init @vm fields (cayman+).
- */
-void radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	vm->id = 0;
-	vm->fence = NULL;
-	vm->last_flush = NULL;
-	vm->last_id_use = NULL;
-	mutex_init(&vm->mutex);
-	INIT_LIST_HEAD(&vm->list);
-	INIT_LIST_HEAD(&vm->va);
-}
-
-/**
- * radeon_vm_fini - tear down a vm instance
- *
- * @rdev: radeon_device pointer
- * @vm: requested vm
- *
- * Tear down @vm (cayman+).
- * Unbind the VM and remove all bos from the vm bo list
- */
-void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
-{
-	struct radeon_bo_va *bo_va, *tmp;
-	int r;
-
-	mutex_lock(&rdev->vm_manager.lock);
-	mutex_lock(&vm->mutex);
-	radeon_vm_free_pt(rdev, vm);
-	mutex_unlock(&rdev->vm_manager.lock);
-
-	if (!list_empty(&vm->va)) {
-		dev_err(rdev->dev, "still active bo inside vm\n");
-	}
-	list_for_each_entry_safe(bo_va, tmp, &vm->va, vm_list) {
-		list_del_init(&bo_va->vm_list);
-		r = radeon_bo_reserve(bo_va->bo, false);
-		if (!r) {
-			list_del_init(&bo_va->bo_list);
-			radeon_bo_unreserve(bo_va->bo);
-			kfree(bo_va);
-		}
-	}
-	radeon_fence_unref(&vm->fence);
-	radeon_fence_unref(&vm->last_flush);
-	radeon_fence_unref(&vm->last_id_use);
-	mutex_unlock(&vm->mutex);
-}
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index b96c819..d09650c 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -344,18 +344,7 @@
 	}
 	robj = gem_to_radeon_bo(gobj);
 	r = radeon_bo_wait(robj, &cur_placement, true);
-	switch (cur_placement) {
-	case TTM_PL_VRAM:
-		args->domain = RADEON_GEM_DOMAIN_VRAM;
-		break;
-	case TTM_PL_TT:
-		args->domain = RADEON_GEM_DOMAIN_GTT;
-		break;
-	case TTM_PL_SYSTEM:
-		args->domain = RADEON_GEM_DOMAIN_CPU;
-	default:
-		break;
-	}
+	args->domain = radeon_mem_type_to_domain(cur_placement);
 	drm_gem_object_unreference_unlocked(gobj);
 	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
@@ -533,6 +522,42 @@
 	return r;
 }
 
+int radeon_gem_op_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *filp)
+{
+	struct drm_radeon_gem_op *args = data;
+	struct drm_gem_object *gobj;
+	struct radeon_bo *robj;
+	int r;
+
+	gobj = drm_gem_object_lookup(dev, filp, args->handle);
+	if (gobj == NULL) {
+		return -ENOENT;
+	}
+	robj = gem_to_radeon_bo(gobj);
+	r = radeon_bo_reserve(robj, false);
+	if (unlikely(r))
+		goto out;
+
+	switch (args->op) {
+	case RADEON_GEM_OP_GET_INITIAL_DOMAIN:
+		args->value = robj->initial_domain;
+		break;
+	case RADEON_GEM_OP_SET_INITIAL_DOMAIN:
+		robj->initial_domain = args->value & (RADEON_GEM_DOMAIN_VRAM |
+						      RADEON_GEM_DOMAIN_GTT |
+						      RADEON_GEM_DOMAIN_CPU);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+	radeon_bo_unreserve(robj);
+out:
+	drm_gem_object_unreference_unlocked(gobj);
+	return r;
+}
+
 int radeon_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_device *dev,
 			    struct drm_mode_create_dumb *args)
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index baff98b..6f1dfac 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -33,6 +33,13 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+
+#if defined(CONFIG_VGA_SWITCHEROO)
+bool radeon_is_px(void);
+#else
+static inline bool radeon_is_px(void) { return false; }
+#endif
+
 /**
  * radeon_driver_unload_kms - Main unload function for KMS.
  *
@@ -130,7 +137,8 @@
 				"Error during ACPI methods call\n");
 	}
 
-	if (radeon_runtime_pm != 0) {
+	if ((radeon_runtime_pm == 1) ||
+	    ((radeon_runtime_pm == -1) && radeon_is_px())) {
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
 		pm_runtime_set_active(dev->dev);
@@ -486,6 +494,21 @@
 	case RADEON_INFO_VCE_FB_VERSION:
 		*value = rdev->vce.fb_version;
 		break;
+	case RADEON_INFO_NUM_BYTES_MOVED:
+		value = (uint32_t*)&value64;
+		value_size = sizeof(uint64_t);
+		value64 = atomic64_read(&rdev->num_bytes_moved);
+		break;
+	case RADEON_INFO_VRAM_USAGE:
+		value = (uint32_t*)&value64;
+		value_size = sizeof(uint64_t);
+		value64 = atomic64_read(&rdev->vram_usage);
+		break;
+	case RADEON_INFO_GTT_USAGE:
+		value = (uint32_t*)&value64;
+		value_size = sizeof(uint64_t);
+		value64 = atomic64_read(&rdev->gtt_usage);
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
@@ -544,7 +567,17 @@
 			return -ENOMEM;
 		}
 
-		radeon_vm_init(rdev, &fpriv->vm);
+		r = radeon_vm_init(rdev, &fpriv->vm);
+		if (r)
+			return r;
+
+		r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+		if (r)
+			return r;
+
+		r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+		if (r)
+			return r;
 
 		/* map the ib pool buffer read only into
 		 * virtual address space */
@@ -553,6 +586,8 @@
 		r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
 					  RADEON_VM_PAGE_READABLE |
 					  RADEON_VM_PAGE_SNOOPED);
+
+		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		if (r) {
 			radeon_vm_fini(rdev, &fpriv->vm);
 			kfree(fpriv);
@@ -814,5 +849,6 @@
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_GET_TILING, radeon_gem_get_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_OP, radeon_gem_op_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 int radeon_max_kms_ioctl = DRM_ARRAY_SIZE(radeon_ioctls_kms);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 08595cf..1375ff8 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -56,11 +56,36 @@
 	}
 }
 
+static void radeon_update_memory_usage(struct radeon_bo *bo,
+				       unsigned mem_type, int sign)
+{
+	struct radeon_device *rdev = bo->rdev;
+	u64 size = (u64)bo->tbo.num_pages << PAGE_SHIFT;
+
+	switch (mem_type) {
+	case TTM_PL_TT:
+		if (sign > 0)
+			atomic64_add(size, &rdev->gtt_usage);
+		else
+			atomic64_sub(size, &rdev->gtt_usage);
+		break;
+	case TTM_PL_VRAM:
+		if (sign > 0)
+			atomic64_add(size, &rdev->vram_usage);
+		else
+			atomic64_sub(size, &rdev->vram_usage);
+		break;
+	}
+}
+
 static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 {
 	struct radeon_bo *bo;
 
 	bo = container_of(tbo, struct radeon_bo, tbo);
+
+	radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);
+
 	mutex_lock(&bo->rdev->gem.mutex);
 	list_del_init(&bo->list);
 	mutex_unlock(&bo->rdev->gem.mutex);
@@ -120,7 +145,6 @@
 
 	size = ALIGN(size, PAGE_SIZE);
 
-	rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
 	if (kernel) {
 		type = ttm_bo_type_kernel;
 	} else if (sg) {
@@ -145,6 +169,9 @@
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
 	INIT_LIST_HEAD(&bo->va);
+	bo->initial_domain = domain & (RADEON_GEM_DOMAIN_VRAM |
+	                               RADEON_GEM_DOMAIN_GTT |
+	                               RADEON_GEM_DOMAIN_CPU);
 	radeon_ttm_placement_from_domain(bo, domain);
 	/* Kernel allocation are uninterruptible */
 	down_read(&rdev->pm.mclk_lock);
@@ -338,39 +365,105 @@
 	arch_phys_wc_del(rdev->mc.vram_mtrr);
 }
 
-void radeon_bo_list_add_object(struct radeon_bo_list *lobj,
-				struct list_head *head)
+/* Returns how many bytes TTM can move per IB.
+ */
+static u64 radeon_bo_get_threshold_for_moves(struct radeon_device *rdev)
 {
-	if (lobj->written) {
-		list_add(&lobj->tv.head, head);
-	} else {
-		list_add_tail(&lobj->tv.head, head);
-	}
+	u64 real_vram_size = rdev->mc.real_vram_size;
+	u64 vram_usage = atomic64_read(&rdev->vram_usage);
+
+	/* This function is based on the current VRAM usage.
+	 *
+	 * - If all of VRAM is free, allow relocating the number of bytes that
+	 *   is equal to 1/4 of the size of VRAM for this IB.
+
+	 * - If more than one half of VRAM is occupied, only allow relocating
+	 *   1 MB of data for this IB.
+	 *
+	 * - From 0 to one half of used VRAM, the threshold decreases
+	 *   linearly.
+	 *         __________________
+	 * 1/4 of -|\               |
+	 * VRAM    | \              |
+	 *         |  \             |
+	 *         |   \            |
+	 *         |    \           |
+	 *         |     \          |
+	 *         |      \         |
+	 *         |       \________|1 MB
+	 *         |----------------|
+	 *    VRAM 0 %             100 %
+	 *         used            used
+	 *
+	 * Note: It's a threshold, not a limit. The threshold must be crossed
+	 * for buffer relocations to stop, so any buffer of an arbitrary size
+	 * can be moved as long as the threshold isn't crossed before
+	 * the relocation takes place. We don't want to disable buffer
+	 * relocations completely.
+	 *
+	 * The idea is that buffers should be placed in VRAM at creation time
+	 * and TTM should only do a minimum number of relocations during
+	 * command submission. In practice, you need to submit at least
+	 * a dozen IBs to move all buffers to VRAM if they are in GTT.
+	 *
+	 * Also, things can get pretty crazy under memory pressure and actual
+	 * VRAM usage can change a lot, so playing safe even at 50% does
+	 * consistently increase performance.
+	 */
+
+	u64 half_vram = real_vram_size >> 1;
+	u64 half_free_vram = vram_usage >= half_vram ? 0 : half_vram - vram_usage;
+	u64 bytes_moved_threshold = half_free_vram >> 1;
+	return max(bytes_moved_threshold, 1024*1024ull);
 }
 
-int radeon_bo_list_validate(struct ww_acquire_ctx *ticket,
+int radeon_bo_list_validate(struct radeon_device *rdev,
+			    struct ww_acquire_ctx *ticket,
 			    struct list_head *head, int ring)
 {
-	struct radeon_bo_list *lobj;
+	struct radeon_cs_reloc *lobj;
 	struct radeon_bo *bo;
-	u32 domain;
 	int r;
+	u64 bytes_moved = 0, initial_bytes_moved;
+	u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);
 
 	r = ttm_eu_reserve_buffers(ticket, head);
 	if (unlikely(r != 0)) {
 		return r;
 	}
+
 	list_for_each_entry(lobj, head, tv.head) {
-		bo = lobj->bo;
+		bo = lobj->robj;
 		if (!bo->pin_count) {
-			domain = lobj->domain;
-			
+			u32 domain = lobj->domain;
+			u32 current_domain =
+				radeon_mem_type_to_domain(bo->tbo.mem.mem_type);
+
+			/* Check if this buffer will be moved and don't move it
+			 * if we have moved too many buffers for this IB already.
+			 *
+			 * Note that this allows moving at least one buffer of
+			 * any size, because it doesn't take the current "bo"
+			 * into account. We don't want to disallow buffer moves
+			 * completely.
+			 */
+			if (current_domain != RADEON_GEM_DOMAIN_CPU &&
+			    (domain & current_domain) == 0 && /* will be moved */
+			    bytes_moved > bytes_moved_threshold) {
+				/* don't move it */
+				domain = current_domain;
+			}
+
 		retry:
 			radeon_ttm_placement_from_domain(bo, domain);
 			if (ring == R600_RING_TYPE_UVD_INDEX)
 				radeon_uvd_force_into_uvd_segment(bo);
-			r = ttm_bo_validate(&bo->tbo, &bo->placement,
-						true, false);
+
+			initial_bytes_moved = atomic64_read(&rdev->num_bytes_moved);
+			r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+			bytes_moved += atomic64_read(&rdev->num_bytes_moved) -
+				       initial_bytes_moved;
+
 			if (unlikely(r)) {
 				if (r != -ERESTARTSYS && domain != lobj->alt_domain) {
 					domain = lobj->alt_domain;
@@ -564,14 +657,23 @@
 }
 
 void radeon_bo_move_notify(struct ttm_buffer_object *bo,
-			   struct ttm_mem_reg *mem)
+			   struct ttm_mem_reg *new_mem)
 {
 	struct radeon_bo *rbo;
+
 	if (!radeon_ttm_bo_is_radeon_bo(bo))
 		return;
+
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	radeon_bo_check_tiling(rbo, 0, 1);
 	radeon_vm_bo_invalidate(rbo->rdev, rbo);
+
+	/* update statistics */
+	if (!new_mem)
+		return;
+
+	radeon_update_memory_usage(rbo, bo->mem.mem_type, -1);
+	radeon_update_memory_usage(rbo, new_mem->mem_type, 1);
 }
 
 int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 209b111..9e7b25a0 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -138,9 +138,8 @@
 extern void radeon_bo_force_delete(struct radeon_device *rdev);
 extern int radeon_bo_init(struct radeon_device *rdev);
 extern void radeon_bo_fini(struct radeon_device *rdev);
-extern void radeon_bo_list_add_object(struct radeon_bo_list *lobj,
-				struct list_head *head);
-extern int radeon_bo_list_validate(struct ww_acquire_ctx *ticket,
+extern int radeon_bo_list_validate(struct radeon_device *rdev,
+				   struct ww_acquire_ctx *ticket,
 				   struct list_head *head, int ring);
 extern int radeon_bo_fbdev_mmap(struct radeon_bo *bo,
 				struct vm_area_struct *vma);
@@ -151,7 +150,7 @@
 extern int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
 				bool force_drop);
 extern void radeon_bo_move_notify(struct ttm_buffer_object *bo,
-					struct ttm_mem_reg *mem);
+				  struct ttm_mem_reg *new_mem);
 extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 extern int radeon_bo_get_surface_reg(struct radeon_bo *bo);
 
@@ -181,7 +180,7 @@
 extern int radeon_sa_bo_new(struct radeon_device *rdev,
 			    struct radeon_sa_manager *sa_manager,
 			    struct radeon_sa_bo **sa_bo,
-			    unsigned size, unsigned align, bool block);
+			    unsigned size, unsigned align);
 extern void radeon_sa_bo_free(struct radeon_device *rdev,
 			      struct radeon_sa_bo **sa_bo,
 			      struct radeon_fence *fence);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 4ad9af9..ee738a5 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -260,7 +260,7 @@
 		if (!ring->ready) {
 			continue;
 		}
-		r = radeon_fence_wait_empty_locked(rdev, i);
+		r = radeon_fence_wait_empty(rdev, i);
 		if (r) {
 			/* needs a GPU reset dont reset here */
 			mutex_unlock(&rdev->ring_lock);
@@ -896,7 +896,7 @@
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
 		struct radeon_ring *ring = &rdev->ring[i];
 		if (ring->ready)
-			radeon_fence_wait_empty_locked(rdev, i);
+			radeon_fence_wait_empty(rdev, i);
 	}
 
 	/* program the new power state */
@@ -943,8 +943,6 @@
 		if (enable) {
 			mutex_lock(&rdev->pm.mutex);
 			rdev->pm.dpm.uvd_active = true;
-			/* disable this for now */
-#if 0
 			if ((rdev->pm.dpm.sd == 1) && (rdev->pm.dpm.hd == 0))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_SD;
 			else if ((rdev->pm.dpm.sd == 2) && (rdev->pm.dpm.hd == 0))
@@ -954,7 +952,6 @@
 			else if ((rdev->pm.dpm.sd == 0) && (rdev->pm.dpm.hd == 2))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD2;
 			else
-#endif
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD;
 			rdev->pm.dpm.state = dpm_state;
 			mutex_unlock(&rdev->pm.mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index b14c86d..8b0dfdd 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -63,7 +63,7 @@
 {
 	int r;
 
-	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256);
 	if (r) {
 		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
 		return r;
@@ -145,6 +145,13 @@
 		return r;
 	}
 
+	/* grab a vm id if necessary */
+	if (ib->vm) {
+		struct radeon_fence *vm_id_fence;
+		vm_id_fence = radeon_vm_grab_id(rdev, ib->vm, ib->ring);
+        	radeon_semaphore_sync_to(ib->semaphore, vm_id_fence);
+	}
+
 	/* sync with other rings */
 	r = radeon_semaphore_sync_rings(rdev, ib->semaphore, ib->ring);
 	if (r) {
@@ -153,11 +160,9 @@
 		return r;
 	}
 
-	/* if we can't remember our last VM flush then flush now! */
-	/* XXX figure out why we have to flush for every IB */
-	if (ib->vm /*&& !ib->vm->last_flush*/) {
-		radeon_ring_vm_flush(rdev, ib->ring, ib->vm);
-	}
+	if (ib->vm)
+		radeon_vm_flush(rdev, ib->vm, ib->ring);
+
 	if (const_ib) {
 		radeon_ring_ib_execute(rdev, const_ib->ring, const_ib);
 		radeon_semaphore_free(rdev, &const_ib->semaphore, NULL);
@@ -172,10 +177,10 @@
 	if (const_ib) {
 		const_ib->fence = radeon_fence_ref(ib->fence);
 	}
-	/* we just flushed the VM, remember that */
-	if (ib->vm && !ib->vm->last_flush) {
-		ib->vm->last_flush = radeon_fence_ref(ib->fence);
-	}
+
+	if (ib->vm)
+		radeon_vm_fence(rdev, ib->vm, ib->fence);
+
 	radeon_ring_unlock_commit(rdev, ring);
 	return 0;
 }
@@ -382,7 +387,7 @@
 		if (ndw < ring->ring_free_dw) {
 			break;
 		}
-		r = radeon_fence_wait_next_locked(rdev, ring->idx);
+		r = radeon_fence_wait_next(rdev, ring->idx);
 		if (r)
 			return r;
 	}
@@ -485,8 +490,8 @@
 void radeon_ring_lockup_update(struct radeon_device *rdev,
 			       struct radeon_ring *ring)
 {
-	ring->last_rptr = radeon_ring_get_rptr(rdev, ring);
-	ring->last_activity = jiffies;
+	atomic_set(&ring->last_rptr, radeon_ring_get_rptr(rdev, ring));
+	atomic64_set(&ring->last_activity, jiffies_64);
 }
 
 /**
@@ -498,22 +503,19 @@
 bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	uint32_t rptr = radeon_ring_get_rptr(rdev, ring);
-	unsigned long cjiffies, elapsed;
+	uint64_t last = atomic64_read(&ring->last_activity);
+	uint64_t elapsed;
 
-	cjiffies = jiffies;
-	if (!time_after(cjiffies, ring->last_activity)) {
-		/* likely a wrap around */
+	if (rptr != atomic_read(&ring->last_rptr)) {
+		/* ring is still working, no lockup */
 		radeon_ring_lockup_update(rdev, ring);
 		return false;
 	}
-	if (rptr != ring->last_rptr) {
-		/* CP is still working no lockup */
-		radeon_ring_lockup_update(rdev, ring);
-		return false;
-	}
-	elapsed = jiffies_to_msecs(cjiffies - ring->last_activity);
+
+	elapsed = jiffies_to_msecs(jiffies_64 - last);
 	if (radeon_lockup_timeout && elapsed >= radeon_lockup_timeout) {
-		dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
+		dev_err(rdev->dev, "ring %d stalled for more than %llumsec\n",
+			ring->idx, elapsed);
 		return true;
 	}
 	/* give a chance to the GPU ... */
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index c062580..adcf3e2 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -312,7 +312,7 @@
 int radeon_sa_bo_new(struct radeon_device *rdev,
 		     struct radeon_sa_manager *sa_manager,
 		     struct radeon_sa_bo **sa_bo,
-		     unsigned size, unsigned align, bool block)
+		     unsigned size, unsigned align)
 {
 	struct radeon_fence *fences[RADEON_NUM_RINGS];
 	unsigned tries[RADEON_NUM_RINGS];
@@ -353,14 +353,11 @@
 		r = radeon_fence_wait_any(rdev, fences, false);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
-		if (r == -ENOENT && block) {
+		if (r == -ENOENT) {
 			r = wait_event_interruptible_locked(
 				sa_manager->wq, 
 				radeon_sa_event(sa_manager, size, align)
 			);
-
-		} else if (r == -ENOENT) {
-			r = -ENOMEM;
 		}
 
 	} while (!r);
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 9006b32..dbd6bcd 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -42,7 +42,7 @@
 		return -ENOMEM;
 	}
 	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &(*semaphore)->sa_bo,
-			     8 * RADEON_NUM_SYNCS, 8, true);
+			     8 * RADEON_NUM_SYNCS, 8);
 	if (r) {
 		kfree(*semaphore);
 		*semaphore = NULL;
@@ -147,7 +147,9 @@
 
 		if (++count > RADEON_NUM_SYNCS) {
 			/* not enough room, wait manually */
-			radeon_fence_wait_locked(fence);
+			r = radeon_fence_wait(fence, false);
+			if (r)
+				return r;
 			continue;
 		}
 
@@ -161,7 +163,9 @@
 		if (!radeon_semaphore_emit_signal(rdev, i, semaphore)) {
 			/* signaling wasn't successful wait manually */
 			radeon_ring_undo(&rdev->ring[i]);
-			radeon_fence_wait_locked(fence);
+			r = radeon_fence_wait(fence, false);
+			if (r)
+				return r;
 			continue;
 		}
 
@@ -169,7 +173,9 @@
 		if (!radeon_semaphore_emit_wait(rdev, ring, semaphore)) {
 			/* waiting wasn't successful wait manually */
 			radeon_ring_undo(&rdev->ring[i]);
-			radeon_fence_wait_locked(fence);
+			r = radeon_fence_wait(fence, false);
+			if (r)
+				return r;
 			continue;
 		}
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 77f5b0c..c8a8a51 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -406,8 +406,14 @@
 	if (r) {
 memcpy:
 		r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
+		if (r) {
+			return r;
+		}
 	}
-	return r;
+
+	/* update statistics */
+	atomic64_add((u64)bo->num_pages << PAGE_SHIFT, &rdev->num_bytes_moved);
+	return 0;
 }
 
 static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
@@ -701,7 +707,9 @@
 	/* No others user of address space so set it to 0 */
 	r = ttm_bo_device_init(&rdev->mman.bdev,
 			       rdev->mman.bo_global_ref.ref.object,
-			       &radeon_bo_driver, DRM_FILE_PAGE_OFFSET,
+			       &radeon_bo_driver,
+			       rdev->ddev->anon_inode->i_mapping,
+			       DRM_FILE_PAGE_OFFSET,
 			       rdev->need_dma32);
 	if (r) {
 		DRM_ERROR("failed initializing buffer object driver(%d).\n", r);
@@ -714,6 +722,9 @@
 		DRM_ERROR("Failed initializing VRAM heap.\n");
 		return r;
 	}
+	/* Change the size here instead of the init above so only lpfn is affected */
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
 	r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true,
 			     RADEON_GEM_DOMAIN_VRAM,
 			     NULL, &rdev->stollen_vga_memory);
@@ -739,7 +750,6 @@
 	}
 	DRM_INFO("radeon: %uM of GTT memory ready.\n",
 		 (unsigned)(rdev->mc.gtt_size / (1024 * 1024)));
-	rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
 
 	r = radeon_ttm_debugfs_init(rdev);
 	if (r) {
@@ -935,7 +945,7 @@
 	while (size) {
 		loff_t p = *pos / PAGE_SIZE;
 		unsigned off = *pos & ~PAGE_MASK;
-		ssize_t cur_size = min(size, PAGE_SIZE - off);
+		size_t cur_size = min_t(size_t, size, PAGE_SIZE - off);
 		struct page *page;
 		void *ptr;
 
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 6781fee..5748bda 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -171,6 +171,8 @@
 
 	radeon_bo_unref(&rdev->uvd.vcpu_bo);
 
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_UVD_INDEX]);
+
 	release_firmware(rdev->uvd_fw);
 }
 
@@ -453,7 +455,7 @@
 	}
 
 	reloc = p->relocs_ptr[(idx / 4)];
-	start = reloc->lobj.gpu_offset;
+	start = reloc->gpu_offset;
 	end = start + radeon_bo_size(reloc->robj);
 	start += offset;
 
@@ -805,8 +807,7 @@
 		    (rdev->pm.dpm.hd != hd)) {
 			rdev->pm.dpm.sd = sd;
 			rdev->pm.dpm.hd = hd;
-			/* disable this for now */
-			/*streams_changed = true;*/
+			streams_changed = true;
 		}
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index d130432..76e9904 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -119,7 +119,7 @@
 	if (rdev->vce.fw_version != ((40 << 24) | (2 << 16) | (2 << 8)))
 		return -EINVAL;
 
-	/* load firmware into VRAM */
+	/* allocate firmware, stack and heap BO */
 
 	size = RADEON_GPU_PAGE_ALIGN(rdev->vce_fw->size) +
 	       RADEON_VCE_STACK_SIZE + RADEON_VCE_HEAP_SIZE;
@@ -130,16 +130,21 @@
 		return r;
 	}
 
-	r = radeon_vce_resume(rdev);
-	if (r)
+	r = radeon_bo_reserve(rdev->vce.vcpu_bo, false);
+	if (r) {
+		radeon_bo_unref(&rdev->vce.vcpu_bo);
+		dev_err(rdev->dev, "(%d) failed to reserve VCE bo\n", r);
 		return r;
+	}
 
-	memset(rdev->vce.cpu_addr, 0, size);
-	memcpy(rdev->vce.cpu_addr, rdev->vce_fw->data, rdev->vce_fw->size);
-
-	r = radeon_vce_suspend(rdev);
-	if (r)
+	r = radeon_bo_pin(rdev->vce.vcpu_bo, RADEON_GEM_DOMAIN_VRAM,
+			  &rdev->vce.gpu_addr);
+	radeon_bo_unreserve(rdev->vce.vcpu_bo);
+	if (r) {
+		radeon_bo_unref(&rdev->vce.vcpu_bo);
+		dev_err(rdev->dev, "(%d) VCE bo pin failed\n", r);
 		return r;
+	}
 
 	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
 		atomic_set(&rdev->vce.handles[i], 0);
@@ -158,8 +163,12 @@
  */
 void radeon_vce_fini(struct radeon_device *rdev)
 {
-	radeon_vce_suspend(rdev);
+	if (rdev->vce.vcpu_bo == NULL)
+		return;
+
 	radeon_bo_unref(&rdev->vce.vcpu_bo);
+
+	release_firmware(rdev->vce_fw);
 }
 
 /**
@@ -167,22 +176,23 @@
  *
  * @rdev: radeon_device pointer
  *
- * TODO: Test VCE suspend/resume
  */
 int radeon_vce_suspend(struct radeon_device *rdev)
 {
-	int r;
+	int i;
 
 	if (rdev->vce.vcpu_bo == NULL)
 		return 0;
 
-	r = radeon_bo_reserve(rdev->vce.vcpu_bo, false);
-	if (!r) {
-		radeon_bo_kunmap(rdev->vce.vcpu_bo);
-		radeon_bo_unpin(rdev->vce.vcpu_bo);
-		radeon_bo_unreserve(rdev->vce.vcpu_bo);
-	}
-	return r;
+	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
+		if (atomic_read(&rdev->vce.handles[i]))
+			break;
+
+	if (i == RADEON_MAX_VCE_HANDLES)
+		return 0;
+
+	/* TODO: suspending running encoding sessions isn't supported */
+	return -EINVAL;
 }
 
 /**
@@ -190,10 +200,10 @@
  *
  * @rdev: radeon_device pointer
  *
- * TODO: Test VCE suspend/resume
  */
 int radeon_vce_resume(struct radeon_device *rdev)
 {
+	void *cpu_addr;
 	int r;
 
 	if (rdev->vce.vcpu_bo == NULL)
@@ -201,26 +211,21 @@
 
 	r = radeon_bo_reserve(rdev->vce.vcpu_bo, false);
 	if (r) {
-		radeon_bo_unref(&rdev->vce.vcpu_bo);
 		dev_err(rdev->dev, "(%d) failed to reserve VCE bo\n", r);
 		return r;
 	}
 
-	r = radeon_bo_pin(rdev->vce.vcpu_bo, RADEON_GEM_DOMAIN_VRAM,
-			  &rdev->vce.gpu_addr);
+	r = radeon_bo_kmap(rdev->vce.vcpu_bo, &cpu_addr);
 	if (r) {
 		radeon_bo_unreserve(rdev->vce.vcpu_bo);
-		radeon_bo_unref(&rdev->vce.vcpu_bo);
-		dev_err(rdev->dev, "(%d) VCE bo pin failed\n", r);
-		return r;
-	}
-
-	r = radeon_bo_kmap(rdev->vce.vcpu_bo, &rdev->vce.cpu_addr);
-	if (r) {
 		dev_err(rdev->dev, "(%d) VCE map failed\n", r);
 		return r;
 	}
 
+	memcpy(cpu_addr, rdev->vce_fw->data, rdev->vce_fw->size);
+
+	radeon_bo_kunmap(rdev->vce.vcpu_bo);
+
 	radeon_bo_unreserve(rdev->vce.vcpu_bo);
 
 	return 0;
@@ -456,7 +461,7 @@
 		return -EINVAL;
 	}
 
-	offset += p->relocs_ptr[(idx / 4)]->lobj.gpu_offset;
+	offset += p->relocs_ptr[(idx / 4)]->gpu_offset;
 
         p->ib.ptr[lo] = offset & 0xFFFFFFFF;
         p->ib.ptr[hi] = offset >> 32;
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
new file mode 100644
index 0000000..2aae6ce
--- /dev/null
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -0,0 +1,966 @@
+/*
+ * Copyright 2008 Advanced Micro Devices, Inc.
+ * Copyright 2008 Red Hat Inc.
+ * Copyright 2009 Jerome Glisse.
+ *
+ * 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
+ *          Alex Deucher
+ *          Jerome Glisse
+ */
+#include <drm/drmP.h>
+#include <drm/radeon_drm.h>
+#include "radeon.h"
+#include "radeon_trace.h"
+
+/*
+ * GPUVM
+ * GPUVM is similar to the legacy gart on older asics, however
+ * rather than there being a single global gart table
+ * for the entire GPU, there are multiple VM page tables active
+ * at any given time.  The VM page tables can contain a mix
+ * vram pages and system memory pages and system memory pages
+ * can be mapped as snooped (cached system pages) or unsnooped
+ * (uncached system pages).
+ * Each VM has an ID associated with it and there is a page table
+ * associated with each VMID.  When execting a command buffer,
+ * the kernel tells the the ring what VMID to use for that command
+ * buffer.  VMIDs are allocated dynamically as commands are submitted.
+ * The userspace drivers maintain their own address space and the kernel
+ * sets up their pages tables accordingly when they submit their
+ * command buffers and a VMID is assigned.
+ * Cayman/Trinity support up to 8 active VMs at any given time;
+ * SI supports 16.
+ */
+
+/**
+ * radeon_vm_num_pde - return the number of page directory entries
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Calculate the number of page directory entries (cayman+).
+ */
+static unsigned radeon_vm_num_pdes(struct radeon_device *rdev)
+{
+	return rdev->vm_manager.max_pfn >> RADEON_VM_BLOCK_SIZE;
+}
+
+/**
+ * radeon_vm_directory_size - returns the size of the page directory in bytes
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Calculate the size of the page directory in bytes (cayman+).
+ */
+static unsigned radeon_vm_directory_size(struct radeon_device *rdev)
+{
+	return RADEON_GPU_PAGE_ALIGN(radeon_vm_num_pdes(rdev) * 8);
+}
+
+/**
+ * radeon_vm_manager_init - init the vm manager
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Init the vm manager (cayman+).
+ * Returns 0 for success, error for failure.
+ */
+int radeon_vm_manager_init(struct radeon_device *rdev)
+{
+	int r;
+
+	if (!rdev->vm_manager.enabled) {
+		r = radeon_asic_vm_init(rdev);
+		if (r)
+			return r;
+
+		rdev->vm_manager.enabled = true;
+	}
+	return 0;
+}
+
+/**
+ * radeon_vm_manager_fini - tear down the vm manager
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Tear down the VM manager (cayman+).
+ */
+void radeon_vm_manager_fini(struct radeon_device *rdev)
+{
+	int i;
+
+	if (!rdev->vm_manager.enabled)
+		return;
+
+	for (i = 0; i < RADEON_NUM_VM; ++i)
+		radeon_fence_unref(&rdev->vm_manager.active[i]);
+	radeon_asic_vm_fini(rdev);
+	rdev->vm_manager.enabled = false;
+}
+
+/**
+ * radeon_vm_get_bos - add the vm BOs to a validation list
+ *
+ * @vm: vm providing the BOs
+ * @head: head of validation list
+ *
+ * Add the page directory to the list of BOs to
+ * validate for command submission (cayman+).
+ */
+struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
+					  struct radeon_vm *vm,
+					  struct list_head *head)
+{
+	struct radeon_cs_reloc *list;
+	unsigned i, idx, size;
+
+	size = (radeon_vm_num_pdes(rdev) + 1) * sizeof(struct radeon_cs_reloc);
+	list = kmalloc(size, GFP_KERNEL);
+	if (!list)
+		return NULL;
+
+	/* add the vm page table to the list */
+	list[0].gobj = NULL;
+	list[0].robj = vm->page_directory;
+	list[0].domain = RADEON_GEM_DOMAIN_VRAM;
+	list[0].alt_domain = RADEON_GEM_DOMAIN_VRAM;
+	list[0].tv.bo = &vm->page_directory->tbo;
+	list[0].tiling_flags = 0;
+	list[0].handle = 0;
+	list_add(&list[0].tv.head, head);
+
+	for (i = 0, idx = 1; i <= vm->max_pde_used; i++) {
+		if (!vm->page_tables[i].bo)
+			continue;
+
+		list[idx].gobj = NULL;
+		list[idx].robj = vm->page_tables[i].bo;
+		list[idx].domain = RADEON_GEM_DOMAIN_VRAM;
+		list[idx].alt_domain = RADEON_GEM_DOMAIN_VRAM;
+		list[idx].tv.bo = &list[idx].robj->tbo;
+		list[idx].tiling_flags = 0;
+		list[idx].handle = 0;
+		list_add(&list[idx++].tv.head, head);
+	}
+
+	return list;
+}
+
+/**
+ * radeon_vm_grab_id - allocate the next free VMID
+ *
+ * @rdev: radeon_device pointer
+ * @vm: vm to allocate id for
+ * @ring: ring we want to submit job to
+ *
+ * Allocate an id for the vm (cayman+).
+ * Returns the fence we need to sync to (if any).
+ *
+ * Global and local mutex must be locked!
+ */
+struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev,
+				       struct radeon_vm *vm, int ring)
+{
+	struct radeon_fence *best[RADEON_NUM_RINGS] = {};
+	unsigned choices[2] = {};
+	unsigned i;
+
+	/* check if the id is still valid */
+	if (vm->last_id_use && vm->last_id_use == rdev->vm_manager.active[vm->id])
+		return NULL;
+
+	/* we definately need to flush */
+	radeon_fence_unref(&vm->last_flush);
+
+	/* skip over VMID 0, since it is the system VM */
+	for (i = 1; i < rdev->vm_manager.nvm; ++i) {
+		struct radeon_fence *fence = rdev->vm_manager.active[i];
+
+		if (fence == NULL) {
+			/* found a free one */
+			vm->id = i;
+			trace_radeon_vm_grab_id(vm->id, ring);
+			return NULL;
+		}
+
+		if (radeon_fence_is_earlier(fence, best[fence->ring])) {
+			best[fence->ring] = fence;
+			choices[fence->ring == ring ? 0 : 1] = i;
+		}
+	}
+
+	for (i = 0; i < 2; ++i) {
+		if (choices[i]) {
+			vm->id = choices[i];
+			trace_radeon_vm_grab_id(vm->id, ring);
+			return rdev->vm_manager.active[choices[i]];
+		}
+	}
+
+	/* should never happen */
+	BUG();
+	return NULL;
+}
+
+/**
+ * radeon_vm_flush - hardware flush the vm
+ *
+ * @rdev: radeon_device pointer
+ * @vm: vm we want to flush
+ * @ring: ring to use for flush
+ *
+ * Flush the vm (cayman+).
+ *
+ * Global and local mutex must be locked!
+ */
+void radeon_vm_flush(struct radeon_device *rdev,
+		     struct radeon_vm *vm,
+		     int ring)
+{
+	uint64_t pd_addr = radeon_bo_gpu_offset(vm->page_directory);
+
+	/* if we can't remember our last VM flush then flush now! */
+	/* XXX figure out why we have to flush all the time */
+	if (!vm->last_flush || true || pd_addr != vm->pd_gpu_addr) {
+		vm->pd_gpu_addr = pd_addr;
+		radeon_ring_vm_flush(rdev, ring, vm);
+	}
+}
+
+/**
+ * radeon_vm_fence - remember fence for vm
+ *
+ * @rdev: radeon_device pointer
+ * @vm: vm we want to fence
+ * @fence: fence to remember
+ *
+ * Fence the vm (cayman+).
+ * Set the fence used to protect page table and id.
+ *
+ * Global and local mutex must be locked!
+ */
+void radeon_vm_fence(struct radeon_device *rdev,
+		     struct radeon_vm *vm,
+		     struct radeon_fence *fence)
+{
+	radeon_fence_unref(&vm->fence);
+	vm->fence = radeon_fence_ref(fence);
+
+	radeon_fence_unref(&rdev->vm_manager.active[vm->id]);
+	rdev->vm_manager.active[vm->id] = radeon_fence_ref(fence);
+
+	radeon_fence_unref(&vm->last_id_use);
+	vm->last_id_use = radeon_fence_ref(fence);
+
+        /* we just flushed the VM, remember that */
+        if (!vm->last_flush)
+                vm->last_flush = radeon_fence_ref(fence);
+}
+
+/**
+ * radeon_vm_bo_find - find the bo_va for a specific vm & bo
+ *
+ * @vm: requested vm
+ * @bo: requested buffer object
+ *
+ * Find @bo inside the requested vm (cayman+).
+ * Search inside the @bos vm list for the requested vm
+ * Returns the found bo_va or NULL if none is found
+ *
+ * Object has to be reserved!
+ */
+struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
+				       struct radeon_bo *bo)
+{
+	struct radeon_bo_va *bo_va;
+
+	list_for_each_entry(bo_va, &bo->va, bo_list) {
+		if (bo_va->vm == vm) {
+			return bo_va;
+		}
+	}
+	return NULL;
+}
+
+/**
+ * radeon_vm_bo_add - add a bo to a specific vm
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ * @bo: radeon buffer object
+ *
+ * Add @bo into the requested vm (cayman+).
+ * Add @bo to the list of bos associated with the vm
+ * Returns newly added bo_va or NULL for failure
+ *
+ * Object has to be reserved!
+ */
+struct radeon_bo_va *radeon_vm_bo_add(struct radeon_device *rdev,
+				      struct radeon_vm *vm,
+				      struct radeon_bo *bo)
+{
+	struct radeon_bo_va *bo_va;
+
+	bo_va = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
+	if (bo_va == NULL) {
+		return NULL;
+	}
+	bo_va->vm = vm;
+	bo_va->bo = bo;
+	bo_va->soffset = 0;
+	bo_va->eoffset = 0;
+	bo_va->flags = 0;
+	bo_va->valid = false;
+	bo_va->ref_count = 1;
+	INIT_LIST_HEAD(&bo_va->bo_list);
+	INIT_LIST_HEAD(&bo_va->vm_list);
+
+	mutex_lock(&vm->mutex);
+	list_add(&bo_va->vm_list, &vm->va);
+	list_add_tail(&bo_va->bo_list, &bo->va);
+	mutex_unlock(&vm->mutex);
+
+	return bo_va;
+}
+
+/**
+ * radeon_vm_clear_bo - initially clear the page dir/table
+ *
+ * @rdev: radeon_device pointer
+ * @bo: bo to clear
+ */
+static int radeon_vm_clear_bo(struct radeon_device *rdev,
+			      struct radeon_bo *bo)
+{
+        struct ttm_validate_buffer tv;
+        struct ww_acquire_ctx ticket;
+        struct list_head head;
+	struct radeon_ib ib;
+	unsigned entries;
+	uint64_t addr;
+	int r;
+
+        memset(&tv, 0, sizeof(tv));
+        tv.bo = &bo->tbo;
+
+        INIT_LIST_HEAD(&head);
+        list_add(&tv.head, &head);
+
+        r = ttm_eu_reserve_buffers(&ticket, &head);
+        if (r)
+		return r;
+
+        r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+        if (r)
+                goto error;
+
+	addr = radeon_bo_gpu_offset(bo);
+	entries = radeon_bo_size(bo) / 8;
+
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib,
+			  NULL, entries * 2 + 64);
+	if (r)
+                goto error;
+
+	ib.length_dw = 0;
+
+	radeon_asic_vm_set_page(rdev, &ib, addr, 0, entries, 0, 0);
+
+	r = radeon_ib_schedule(rdev, &ib, NULL);
+	if (r)
+                goto error;
+
+	ttm_eu_fence_buffer_objects(&ticket, &head, ib.fence);
+	radeon_ib_free(rdev, &ib);
+
+	return 0;
+
+error:
+	ttm_eu_backoff_reservation(&ticket, &head);
+	return r;
+}
+
+/**
+ * radeon_vm_bo_set_addr - set bos virtual address inside a vm
+ *
+ * @rdev: radeon_device pointer
+ * @bo_va: bo_va to store the address
+ * @soffset: requested offset of the buffer in the VM address space
+ * @flags: attributes of pages (read/write/valid/etc.)
+ *
+ * Set offset of @bo_va (cayman+).
+ * Validate and set the offset requested within the vm address space.
+ * Returns 0 for success, error for failure.
+ *
+ * Object has to be reserved!
+ */
+int radeon_vm_bo_set_addr(struct radeon_device *rdev,
+			  struct radeon_bo_va *bo_va,
+			  uint64_t soffset,
+			  uint32_t flags)
+{
+	uint64_t size = radeon_bo_size(bo_va->bo);
+	uint64_t eoffset, last_offset = 0;
+	struct radeon_vm *vm = bo_va->vm;
+	struct radeon_bo_va *tmp;
+	struct list_head *head;
+	unsigned last_pfn, pt_idx;
+	int r;
+
+	if (soffset) {
+		/* make sure object fit at this offset */
+		eoffset = soffset + size;
+		if (soffset >= eoffset) {
+			return -EINVAL;
+		}
+
+		last_pfn = eoffset / RADEON_GPU_PAGE_SIZE;
+		if (last_pfn > rdev->vm_manager.max_pfn) {
+			dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n",
+				last_pfn, rdev->vm_manager.max_pfn);
+			return -EINVAL;
+		}
+
+	} else {
+		eoffset = last_pfn = 0;
+	}
+
+	mutex_lock(&vm->mutex);
+	head = &vm->va;
+	last_offset = 0;
+	list_for_each_entry(tmp, &vm->va, vm_list) {
+		if (bo_va == tmp) {
+			/* skip over currently modified bo */
+			continue;
+		}
+
+		if (soffset >= last_offset && eoffset <= tmp->soffset) {
+			/* bo can be added before this one */
+			break;
+		}
+		if (eoffset > tmp->soffset && soffset < tmp->eoffset) {
+			/* bo and tmp overlap, invalid offset */
+			dev_err(rdev->dev, "bo %p va 0x%08X conflict with (bo %p 0x%08X 0x%08X)\n",
+				bo_va->bo, (unsigned)bo_va->soffset, tmp->bo,
+				(unsigned)tmp->soffset, (unsigned)tmp->eoffset);
+			mutex_unlock(&vm->mutex);
+			return -EINVAL;
+		}
+		last_offset = tmp->eoffset;
+		head = &tmp->vm_list;
+	}
+
+	bo_va->soffset = soffset;
+	bo_va->eoffset = eoffset;
+	bo_va->flags = flags;
+	bo_va->valid = false;
+	list_move(&bo_va->vm_list, head);
+
+	soffset = (soffset / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE;
+	eoffset = (eoffset / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE;
+
+	if (eoffset > vm->max_pde_used)
+		vm->max_pde_used = eoffset;
+
+	radeon_bo_unreserve(bo_va->bo);
+
+	/* walk over the address space and allocate the page tables */
+	for (pt_idx = soffset; pt_idx <= eoffset; ++pt_idx) {
+		struct radeon_bo *pt;
+
+		if (vm->page_tables[pt_idx].bo)
+			continue;
+
+		/* drop mutex to allocate and clear page table */
+		mutex_unlock(&vm->mutex);
+
+		r = radeon_bo_create(rdev, RADEON_VM_PTE_COUNT * 8,
+				     RADEON_GPU_PAGE_SIZE, false, 
+				     RADEON_GEM_DOMAIN_VRAM, NULL, &pt);
+		if (r)
+			return r;
+
+		r = radeon_vm_clear_bo(rdev, pt);
+		if (r) {
+			radeon_bo_unref(&pt);
+			radeon_bo_reserve(bo_va->bo, false);
+			return r;
+		}
+
+		/* aquire mutex again */
+		mutex_lock(&vm->mutex);
+		if (vm->page_tables[pt_idx].bo) {
+			/* someone else allocated the pt in the meantime */
+			mutex_unlock(&vm->mutex);
+			radeon_bo_unref(&pt);
+			mutex_lock(&vm->mutex);
+			continue;
+		}
+
+		vm->page_tables[pt_idx].addr = 0;
+		vm->page_tables[pt_idx].bo = pt;
+	}
+
+	mutex_unlock(&vm->mutex);
+	return radeon_bo_reserve(bo_va->bo, false);
+}
+
+/**
+ * radeon_vm_map_gart - get the physical address of a gart page
+ *
+ * @rdev: radeon_device pointer
+ * @addr: the unmapped addr
+ *
+ * Look up the physical address of the page that the pte resolves
+ * to (cayman+).
+ * Returns the physical address of the page.
+ */
+uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr)
+{
+	uint64_t result;
+
+	/* page table offset */
+	result = rdev->gart.pages_addr[addr >> PAGE_SHIFT];
+
+	/* in case cpu page size != gpu page size*/
+	result |= addr & (~PAGE_MASK);
+
+	return result;
+}
+
+/**
+ * radeon_vm_page_flags - translate page flags to what the hw uses
+ *
+ * @flags: flags comming from userspace
+ *
+ * Translate the flags the userspace ABI uses to hw flags.
+ */
+static uint32_t radeon_vm_page_flags(uint32_t flags)
+{
+        uint32_t hw_flags = 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_VALID) ? R600_PTE_VALID : 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_READABLE) ? R600_PTE_READABLE : 0;
+        hw_flags |= (flags & RADEON_VM_PAGE_WRITEABLE) ? R600_PTE_WRITEABLE : 0;
+        if (flags & RADEON_VM_PAGE_SYSTEM) {
+                hw_flags |= R600_PTE_SYSTEM;
+                hw_flags |= (flags & RADEON_VM_PAGE_SNOOPED) ? R600_PTE_SNOOPED : 0;
+        }
+        return hw_flags;
+}
+
+/**
+ * radeon_vm_update_pdes - make sure that page directory is valid
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ * @start: start of GPU address range
+ * @end: end of GPU address range
+ *
+ * Allocates new page tables if necessary
+ * and updates the page directory (cayman+).
+ * Returns 0 for success, error for failure.
+ *
+ * Global and local mutex must be locked!
+ */
+int radeon_vm_update_page_directory(struct radeon_device *rdev,
+				    struct radeon_vm *vm)
+{
+	static const uint32_t incr = RADEON_VM_PTE_COUNT * 8;
+
+	uint64_t pd_addr = radeon_bo_gpu_offset(vm->page_directory);
+	uint64_t last_pde = ~0, last_pt = ~0;
+	unsigned count = 0, pt_idx, ndw;
+	struct radeon_ib ib;
+	int r;
+
+	/* padding, etc. */
+	ndw = 64;
+
+	/* assume the worst case */
+	ndw += vm->max_pde_used * 12;
+
+	/* update too big for an IB */
+	if (ndw > 0xfffff)
+		return -ENOMEM;
+
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib, NULL, ndw * 4);
+	if (r)
+		return r;
+	ib.length_dw = 0;
+
+	/* walk over the address space and update the page directory */
+	for (pt_idx = 0; pt_idx <= vm->max_pde_used; ++pt_idx) {
+		struct radeon_bo *bo = vm->page_tables[pt_idx].bo;
+		uint64_t pde, pt;
+
+		if (bo == NULL)
+			continue;
+
+		pt = radeon_bo_gpu_offset(bo);
+		if (vm->page_tables[pt_idx].addr == pt)
+			continue;
+		vm->page_tables[pt_idx].addr = pt;
+
+		pde = pd_addr + pt_idx * 8;
+		if (((last_pde + 8 * count) != pde) ||
+		    ((last_pt + incr * count) != pt)) {
+
+			if (count) {
+				radeon_asic_vm_set_page(rdev, &ib, last_pde,
+							last_pt, count, incr,
+							R600_PTE_VALID);
+			}
+
+			count = 1;
+			last_pde = pde;
+			last_pt = pt;
+		} else {
+			++count;
+		}
+	}
+
+	if (count)
+		radeon_asic_vm_set_page(rdev, &ib, last_pde, last_pt, count,
+					incr, R600_PTE_VALID);
+
+	if (ib.length_dw != 0) {
+		radeon_semaphore_sync_to(ib.semaphore, vm->last_id_use);
+		r = radeon_ib_schedule(rdev, &ib, NULL);
+		if (r) {
+			radeon_ib_free(rdev, &ib);
+			return r;
+		}
+		radeon_fence_unref(&vm->fence);
+		vm->fence = radeon_fence_ref(ib.fence);
+		radeon_fence_unref(&vm->last_flush);
+	}
+	radeon_ib_free(rdev, &ib);
+
+	return 0;
+}
+
+/**
+ * radeon_vm_update_ptes - make sure that page tables are valid
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ * @start: start of GPU address range
+ * @end: end of GPU address range
+ * @dst: destination address to map to
+ * @flags: mapping flags
+ *
+ * Update the page tables in the range @start - @end (cayman+).
+ *
+ * Global and local mutex must be locked!
+ */
+static void radeon_vm_update_ptes(struct radeon_device *rdev,
+				  struct radeon_vm *vm,
+				  struct radeon_ib *ib,
+				  uint64_t start, uint64_t end,
+				  uint64_t dst, uint32_t flags)
+{
+	static const uint64_t mask = RADEON_VM_PTE_COUNT - 1;
+
+	uint64_t last_pte = ~0, last_dst = ~0;
+	unsigned count = 0;
+	uint64_t addr;
+
+	start = start / RADEON_GPU_PAGE_SIZE;
+	end = end / RADEON_GPU_PAGE_SIZE;
+
+	/* walk over the address space and update the page tables */
+	for (addr = start; addr < end; ) {
+		uint64_t pt_idx = addr >> RADEON_VM_BLOCK_SIZE;
+		unsigned nptes;
+		uint64_t pte;
+
+		if ((addr & ~mask) == (end & ~mask))
+			nptes = end - addr;
+		else
+			nptes = RADEON_VM_PTE_COUNT - (addr & mask);
+
+		pte = radeon_bo_gpu_offset(vm->page_tables[pt_idx].bo);
+		pte += (addr & mask) * 8;
+
+		if ((last_pte + 8 * count) != pte) {
+
+			if (count) {
+				radeon_asic_vm_set_page(rdev, ib, last_pte,
+							last_dst, count,
+							RADEON_GPU_PAGE_SIZE,
+							flags);
+			}
+
+			count = nptes;
+			last_pte = pte;
+			last_dst = dst;
+		} else {
+			count += nptes;
+		}
+
+		addr += nptes;
+		dst += nptes * RADEON_GPU_PAGE_SIZE;
+	}
+
+	if (count) {
+		radeon_asic_vm_set_page(rdev, ib, last_pte,
+					last_dst, count,
+					RADEON_GPU_PAGE_SIZE, flags);
+	}
+}
+
+/**
+ * radeon_vm_bo_update - map a bo into the vm page table
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ * @bo: radeon buffer object
+ * @mem: ttm mem
+ *
+ * Fill in the page table entries for @bo (cayman+).
+ * Returns 0 for success, -EINVAL for failure.
+ *
+ * Object have to be reserved and mutex must be locked!
+ */
+int radeon_vm_bo_update(struct radeon_device *rdev,
+			struct radeon_vm *vm,
+			struct radeon_bo *bo,
+			struct ttm_mem_reg *mem)
+{
+	struct radeon_ib ib;
+	struct radeon_bo_va *bo_va;
+	unsigned nptes, ndw;
+	uint64_t addr;
+	int r;
+
+	bo_va = radeon_vm_bo_find(vm, bo);
+	if (bo_va == NULL) {
+		dev_err(rdev->dev, "bo %p not in vm %p\n", bo, vm);
+		return -EINVAL;
+	}
+
+	if (!bo_va->soffset) {
+		dev_err(rdev->dev, "bo %p don't has a mapping in vm %p\n",
+			bo, vm);
+		return -EINVAL;
+	}
+
+	if ((bo_va->valid && mem) || (!bo_va->valid && mem == NULL))
+		return 0;
+
+	bo_va->flags &= ~RADEON_VM_PAGE_VALID;
+	bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM;
+	if (mem) {
+		addr = mem->start << PAGE_SHIFT;
+		if (mem->mem_type != TTM_PL_SYSTEM) {
+			bo_va->flags |= RADEON_VM_PAGE_VALID;
+			bo_va->valid = true;
+		}
+		if (mem->mem_type == TTM_PL_TT) {
+			bo_va->flags |= RADEON_VM_PAGE_SYSTEM;
+		} else {
+			addr += rdev->vm_manager.vram_base_offset;
+		}
+	} else {
+		addr = 0;
+		bo_va->valid = false;
+	}
+
+	trace_radeon_vm_bo_update(bo_va);
+
+	nptes = radeon_bo_ngpu_pages(bo);
+
+	/* padding, etc. */
+	ndw = 64;
+
+	if (RADEON_VM_BLOCK_SIZE > 11)
+		/* reserve space for one header for every 2k dwords */
+		ndw += (nptes >> 11) * 4;
+	else
+		/* reserve space for one header for
+		    every (1 << BLOCK_SIZE) entries */
+		ndw += (nptes >> RADEON_VM_BLOCK_SIZE) * 4;
+
+	/* reserve space for pte addresses */
+	ndw += nptes * 2;
+
+	/* update too big for an IB */
+	if (ndw > 0xfffff)
+		return -ENOMEM;
+
+	r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib, NULL, ndw * 4);
+	if (r)
+		return r;
+	ib.length_dw = 0;
+
+	radeon_vm_update_ptes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset,
+			      addr, radeon_vm_page_flags(bo_va->flags));
+
+	radeon_semaphore_sync_to(ib.semaphore, vm->fence);
+	r = radeon_ib_schedule(rdev, &ib, NULL);
+	if (r) {
+		radeon_ib_free(rdev, &ib);
+		return r;
+	}
+	radeon_fence_unref(&vm->fence);
+	vm->fence = radeon_fence_ref(ib.fence);
+	radeon_ib_free(rdev, &ib);
+	radeon_fence_unref(&vm->last_flush);
+
+	return 0;
+}
+
+/**
+ * radeon_vm_bo_rmv - remove a bo to a specific vm
+ *
+ * @rdev: radeon_device pointer
+ * @bo_va: requested bo_va
+ *
+ * Remove @bo_va->bo from the requested vm (cayman+).
+ * Remove @bo_va->bo from the list of bos associated with the bo_va->vm and
+ * remove the ptes for @bo_va in the page table.
+ * Returns 0 for success.
+ *
+ * Object have to be reserved!
+ */
+int radeon_vm_bo_rmv(struct radeon_device *rdev,
+		     struct radeon_bo_va *bo_va)
+{
+	int r = 0;
+
+	mutex_lock(&bo_va->vm->mutex);
+	if (bo_va->soffset)
+		r = radeon_vm_bo_update(rdev, bo_va->vm, bo_va->bo, NULL);
+
+	list_del(&bo_va->vm_list);
+	mutex_unlock(&bo_va->vm->mutex);
+	list_del(&bo_va->bo_list);
+
+	kfree(bo_va);
+	return r;
+}
+
+/**
+ * radeon_vm_bo_invalidate - mark the bo as invalid
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ * @bo: radeon buffer object
+ *
+ * Mark @bo as invalid (cayman+).
+ */
+void radeon_vm_bo_invalidate(struct radeon_device *rdev,
+			     struct radeon_bo *bo)
+{
+	struct radeon_bo_va *bo_va;
+
+	list_for_each_entry(bo_va, &bo->va, bo_list) {
+		bo_va->valid = false;
+	}
+}
+
+/**
+ * radeon_vm_init - initialize a vm instance
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ *
+ * Init @vm fields (cayman+).
+ */
+int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
+{
+	unsigned pd_size, pd_entries, pts_size;
+	int r;
+
+	vm->id = 0;
+	vm->fence = NULL;
+	vm->last_flush = NULL;
+	vm->last_id_use = NULL;
+	mutex_init(&vm->mutex);
+	INIT_LIST_HEAD(&vm->va);
+
+	pd_size = radeon_vm_directory_size(rdev);
+	pd_entries = radeon_vm_num_pdes(rdev);
+
+	/* allocate page table array */
+	pts_size = pd_entries * sizeof(struct radeon_vm_pt);
+	vm->page_tables = kzalloc(pts_size, GFP_KERNEL);
+	if (vm->page_tables == NULL) {
+		DRM_ERROR("Cannot allocate memory for page table array\n");
+		return -ENOMEM;
+	}
+
+	r = radeon_bo_create(rdev, pd_size, RADEON_VM_PTB_ALIGN_SIZE, false,
+			     RADEON_GEM_DOMAIN_VRAM, NULL,
+			     &vm->page_directory);
+	if (r)
+		return r;
+
+	r = radeon_vm_clear_bo(rdev, vm->page_directory);
+	if (r) {
+		radeon_bo_unref(&vm->page_directory);
+		vm->page_directory = NULL;
+		return r;
+	}
+
+	return 0;
+}
+
+/**
+ * radeon_vm_fini - tear down a vm instance
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ *
+ * Tear down @vm (cayman+).
+ * Unbind the VM and remove all bos from the vm bo list
+ */
+void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
+{
+	struct radeon_bo_va *bo_va, *tmp;
+	int i, r;
+
+	if (!list_empty(&vm->va)) {
+		dev_err(rdev->dev, "still active bo inside vm\n");
+	}
+	list_for_each_entry_safe(bo_va, tmp, &vm->va, vm_list) {
+		list_del_init(&bo_va->vm_list);
+		r = radeon_bo_reserve(bo_va->bo, false);
+		if (!r) {
+			list_del_init(&bo_va->bo_list);
+			radeon_bo_unreserve(bo_va->bo);
+			kfree(bo_va);
+		}
+	}
+
+
+	for (i = 0; i < radeon_vm_num_pdes(rdev); i++)
+		radeon_bo_unref(&vm->page_tables[i].bo);
+	kfree(vm->page_tables);
+
+	radeon_bo_unref(&vm->page_directory);
+
+	radeon_fence_unref(&vm->fence);
+	radeon_fence_unref(&vm->last_flush);
+	radeon_fence_unref(&vm->last_id_use);
+
+	mutex_destroy(&vm->mutex);
+}
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index b5c2369..130d5cc 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -474,8 +474,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = rs400_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index fdcde76..72d3616 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -1048,8 +1048,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = rs600_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3595073..3462b64 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -756,8 +756,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r = rs690_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 98e8138..237dd29 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -586,8 +586,6 @@
 	/* Initialize surface registers */
 	radeon_surface_init(rdev);
 
-	radeon_pm_resume(rdev);
-
 	rdev->accel_working = true;
 	r =  rv515_startup(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 6c772e5..fef3107 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1811,7 +1811,8 @@
 	/* init golden registers */
 	rv770_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = rv770_startup(rdev);
@@ -1955,9 +1956,9 @@
 	radeon_wb_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	rv770_pcie_gart_fini(rdev);
 	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
+	rv770_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
 	radeon_fence_driver_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 8008cb8..d589475 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6610,7 +6610,8 @@
 	/* init golden registers */
 	si_init_golden_registers(rdev);
 
-	radeon_pm_resume(rdev);
+	if (rdev->pm.pm_method == PM_METHOD_DPM)
+		radeon_pm_resume(rdev);
 
 	rdev->accel_working = true;
 	r = si_startup(rdev);
diff --git a/drivers/gpu/drm/tegra/bus.c b/drivers/gpu/drm/tegra/bus.c
index e38e596..71cef5c 100644
--- a/drivers/gpu/drm/tegra/bus.c
+++ b/drivers/gpu/drm/tegra/bus.c
@@ -63,7 +63,7 @@
 	return 0;
 
 err_free:
-	drm_dev_free(drm);
+	drm_dev_unref(drm);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 88a5290..c715947 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -104,7 +104,7 @@
 
 static void tegra_drm_lastclose(struct drm_device *drm)
 {
-#ifdef CONFIG_TEGRA_DRM_FBDEV
+#ifdef CONFIG_DRM_TEGRA_FBDEV
 	struct tegra_drm *tegra = drm->dev_private;
 
 	tegra_fbdev_restore_mode(tegra->fbdev);
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 338f7f6..0266fb4 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -15,6 +15,7 @@
 struct tegra_rgb {
 	struct tegra_output output;
 	struct tegra_dc *dc;
+	bool enabled;
 
 	struct clk *clk_parent;
 	struct clk *clk;
@@ -89,6 +90,9 @@
 	struct tegra_rgb *rgb = to_rgb(output);
 	unsigned long value;
 
+	if (rgb->enabled)
+		return 0;
+
 	tegra_dc_write_regs(rgb->dc, rgb_enable, ARRAY_SIZE(rgb_enable));
 
 	value = DE_SELECT_ACTIVE | DE_CONTROL_NORMAL;
@@ -122,6 +126,8 @@
 	tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
 	tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL);
 
+	rgb->enabled = true;
+
 	return 0;
 }
 
@@ -130,6 +136,9 @@
 	struct tegra_rgb *rgb = to_rgb(output);
 	unsigned long value;
 
+	if (!rgb->enabled)
+		return 0;
+
 	value = tegra_dc_readl(rgb->dc, DC_CMD_DISPLAY_POWER_CONTROL);
 	value &= ~(PW0_ENABLE | PW1_ENABLE | PW2_ENABLE | PW3_ENABLE |
 		   PW4_ENABLE | PM0_ENABLE | PM1_ENABLE);
@@ -144,6 +153,8 @@
 
 	tegra_dc_write_regs(rgb->dc, rgb_disable, ARRAY_SIZE(rgb_disable));
 
+	rgb->enabled = false;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a066513..9df79ac 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -351,9 +351,11 @@
 
 moved:
 	if (bo->evicted) {
-		ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
-		if (ret)
-			pr_err("Can not flush read caches\n");
+		if (bdev->driver->invalidate_caches) {
+			ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
+			if (ret)
+				pr_err("Can not flush read caches\n");
+		}
 		bo->evicted = false;
 	}
 
@@ -1449,6 +1451,7 @@
 int ttm_bo_device_init(struct ttm_bo_device *bdev,
 		       struct ttm_bo_global *glob,
 		       struct ttm_bo_driver *driver,
+		       struct address_space *mapping,
 		       uint64_t file_page_offset,
 		       bool need_dma32)
 {
@@ -1470,7 +1473,7 @@
 				    0x10000000);
 	INIT_DELAYED_WORK(&bdev->wq, ttm_bo_delayed_workqueue);
 	INIT_LIST_HEAD(&bdev->ddestroy);
-	bdev->dev_mapping = NULL;
+	bdev->dev_mapping = mapping;
 	bdev->glob = glob;
 	bdev->need_dma32 = need_dma32;
 	bdev->val_seq = 0;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 801231c..0ce48e5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -339,11 +339,13 @@
 	vma->vm_private_data = bo;
 
 	/*
-	 * PFNMAP is faster than MIXEDMAP due to reduced page
-	 * administration. So use MIXEDMAP only if private VMA, where
-	 * we need to support COW.
+	 * We'd like to use VM_PFNMAP on shared mappings, where
+	 * (vma->vm_flags & VM_SHARED) != 0, for performance reasons,
+	 * but for some reason VM_PFNMAP + x86 PAT + write-combine is very
+	 * bad for performance. Until that has been sorted out, use
+	 * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719
 	 */
-	vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 out_unref:
@@ -359,7 +361,7 @@
 
 	vma->vm_ops = &ttm_bo_vm_ops;
 	vma->vm_private_data = ttm_bo_reference(bo);
-	vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND;
 	return 0;
 }
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index dbadd49..3771763 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -421,7 +421,7 @@
 				  clips[i].x2 - clips[i].x1,
 				  clips[i].y2 - clips[i].y1);
 		if (ret)
-			goto unlock;
+			break;
 	}
 
 	if (ufb->obj->base.import_attach) {
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 8d67b94..be4fcd0 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -60,7 +60,7 @@
 		    struct drm_device *dev,
 		    struct drm_mode_create_dumb *args)
 {
-	args->pitch = args->width * ((args->bpp + 1) / 8);
+	args->pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
 	args->size = args->pitch * args->height;
 	return udl_gem_create(file, dev,
 			      args->size, &args->handle);
diff --git a/drivers/gpu/drm/vmwgfx/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/svga3d_reg.h
index bb594c1..f58dc7d 100644
--- a/drivers/gpu/drm/vmwgfx/svga3d_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga3d_reg.h
@@ -261,12 +261,7 @@
    /* Planar video formats. */
    SVGA3D_YV12                         = 121,
 
-   /* Shader constant formats. */
-   SVGA3D_SURFACE_SHADERCONST_FLOAT    = 122,
-   SVGA3D_SURFACE_SHADERCONST_INT      = 123,
-   SVGA3D_SURFACE_SHADERCONST_BOOL     = 124,
-
-   SVGA3D_FORMAT_MAX                   = 125,
+   SVGA3D_FORMAT_MAX                   = 122,
 } SVGA3dSurfaceFormat;
 
 typedef uint32 SVGA3dColor; /* a, r, g, b */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 0083cbf..c35715f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -722,7 +722,9 @@
 
 	ret = ttm_bo_device_init(&dev_priv->bdev,
 				 dev_priv->bo_global_ref.ref.object,
-				 &vmw_bo_driver, VMWGFX_FILE_PAGE_OFFSET,
+				 &vmw_bo_driver,
+				 dev->anon_inode->i_mapping,
+				 VMWGFX_FILE_PAGE_OFFSET,
 				 false);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Failed initializing TTM buffer object driver.\n");
@@ -969,7 +971,6 @@
 		goto out_no_shman;
 
 	file_priv->driver_priv = vmw_fp;
-	dev_priv->bdev.dev_mapping = dev->dev_mapping;
 
 	return 0;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 9e4be17..0783155 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -40,7 +40,7 @@
 #include <drm/ttm/ttm_module.h>
 #include "vmwgfx_fence.h"
 
-#define VMWGFX_DRIVER_DATE "20121114"
+#define VMWGFX_DRIVER_DATE "20140228"
 #define VMWGFX_DRIVER_MAJOR 2
 #define VMWGFX_DRIVER_MINOR 5
 #define VMWGFX_DRIVER_PATCHLEVEL 0
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index d4a5a19..04a64b8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -188,18 +188,20 @@
 
 	bo = otable->page_table->pt_bo;
 	cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
-	if (unlikely(cmd == NULL))
-		DRM_ERROR("Failed reserving FIFO space for OTable setup.\n");
-
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE;
-	cmd->header.size = sizeof(cmd->body);
-	cmd->body.type = type;
-	cmd->body.baseAddress = 0;
-	cmd->body.sizeInBytes = 0;
-	cmd->body.validSizeInBytes = 0;
-	cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID;
-	vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	if (unlikely(cmd == NULL)) {
+		DRM_ERROR("Failed reserving FIFO space for OTable "
+			  "takedown.\n");
+	} else {
+		memset(cmd, 0, sizeof(*cmd));
+		cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE;
+		cmd->header.size = sizeof(cmd->body);
+		cmd->body.type = type;
+		cmd->body.baseAddress = 0;
+		cmd->body.sizeInBytes = 0;
+		cmd->body.validSizeInBytes = 0;
+		cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID;
+		vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	}
 
 	if (bo) {
 		int ret;
@@ -562,11 +564,12 @@
 	if (unlikely(cmd == NULL)) {
 		DRM_ERROR("Failed reserving FIFO space for Memory "
 			  "Object unbinding.\n");
+	} else {
+		cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB;
+		cmd->header.size = sizeof(cmd->body);
+		cmd->body.mobid = mob->id;
+		vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	}
-	cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB;
-	cmd->header.size = sizeof(cmd->body);
-	cmd->body.mobid = mob->id;
-	vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	if (bo) {
 		vmw_fence_single_bo(bo, NULL);
 		ttm_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 2aa4bc6..9757b57 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -427,8 +427,7 @@
 	INIT_LIST_HEAD(&vmw_bo->res_list);
 
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
-			  (user) ? ttm_bo_type_device :
-			  ttm_bo_type_kernel, placement,
+			  ttm_bo_type_device, placement,
 			  0, interruptible,
 			  NULL, acc_size, NULL, bo_free);
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 82468d9..e7af580 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -830,6 +830,24 @@
 	if (unlikely(ret != 0))
 		goto out_unlock;
 
+	/*
+	 * A gb-aware client referencing a shared surface will
+	 * expect a backup buffer to be present.
+	 */
+	if (dev_priv->has_mob && req->shareable) {
+		uint32_t backup_handle;
+
+		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
+					    res->backup_size,
+					    true,
+					    &backup_handle,
+					    &res->backup);
+		if (unlikely(ret != 0)) {
+			vmw_resource_unreference(&res);
+			goto out_unlock;
+		}
+	}
+
 	tmp = vmw_resource_reference(&srf->res);
 	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
 				    req->shareable, VMW_RES_SURFACE,
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 1146e3b..112f27e 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -538,7 +538,7 @@
 
 		g->base = job->gather_addr_phys[i];
 
-		for (j = 0; j < job->num_gathers; j++)
+		for (j = i + 1; j < job->num_gathers; j++)
 			if (job->gathers[j].bo == g->bo)
 				job->gathers[j].handled = true;
 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index f5ed031..de17c55 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -387,7 +387,7 @@
 
 config I2C_CPM
 	tristate "Freescale CPM1 or CPM2 (MPC8xx/826x)"
-	depends on (CPM1 || CPM2) && OF_I2C
+	depends on CPM1 || CPM2
 	help
 	  This supports the use of the I2C interface on Freescale
 	  processors with CPM1 or CPM2.
diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig
index 41c64a4..ac2d69e 100644
--- a/drivers/iio/gyro/Kconfig
+++ b/drivers/iio/gyro/Kconfig
@@ -70,7 +70,7 @@
 	select IIO_TRIGGERED_BUFFER if (IIO_BUFFER)
 	help
 	  Say yes here to build support for STMicroelectronics gyroscopes:
-	  L3G4200D, LSM330DL, L3GD20, L3GD20H, LSM330DLC, L3G4IS, LSM330.
+	  L3G4200D, LSM330DL, L3GD20, LSM330DLC, L3G4IS, LSM330.
 
 	  This driver can also be built as a module. If so, these modules
 	  will be created:
diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h
index f8f2bf8..c197360 100644
--- a/drivers/iio/gyro/st_gyro.h
+++ b/drivers/iio/gyro/st_gyro.h
@@ -19,7 +19,6 @@
 #define LSM330DL_GYRO_DEV_NAME		"lsm330dl_gyro"
 #define LSM330DLC_GYRO_DEV_NAME		"lsm330dlc_gyro"
 #define L3GD20_GYRO_DEV_NAME		"l3gd20"
-#define L3GD20H_GYRO_DEV_NAME		"l3gd20h"
 #define L3G4IS_GYRO_DEV_NAME		"l3g4is_ui"
 #define LSM330_GYRO_DEV_NAME		"lsm330_gyro"
 
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index d53d91a..a8e174a 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -167,11 +167,10 @@
 		.wai = ST_GYRO_2_WAI_EXP,
 		.sensors_supported = {
 			[0] = L3GD20_GYRO_DEV_NAME,
-			[1] = L3GD20H_GYRO_DEV_NAME,
-			[2] = LSM330D_GYRO_DEV_NAME,
-			[3] = LSM330DLC_GYRO_DEV_NAME,
-			[4] = L3G4IS_GYRO_DEV_NAME,
-			[5] = LSM330_GYRO_DEV_NAME,
+			[1] = LSM330D_GYRO_DEV_NAME,
+			[2] = LSM330DLC_GYRO_DEV_NAME,
+			[3] = L3G4IS_GYRO_DEV_NAME,
+			[4] = LSM330_GYRO_DEV_NAME,
 		},
 		.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
 		.odr = {
diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c
index 16b8b8d..23c12f3 100644
--- a/drivers/iio/gyro/st_gyro_i2c.c
+++ b/drivers/iio/gyro/st_gyro_i2c.c
@@ -55,7 +55,6 @@
 	{ LSM330DL_GYRO_DEV_NAME },
 	{ LSM330DLC_GYRO_DEV_NAME },
 	{ L3GD20_GYRO_DEV_NAME },
-	{ L3GD20H_GYRO_DEV_NAME },
 	{ L3G4IS_GYRO_DEV_NAME },
 	{ LSM330_GYRO_DEV_NAME },
 	{},
diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c
index 94763e2..b4ad3be 100644
--- a/drivers/iio/gyro/st_gyro_spi.c
+++ b/drivers/iio/gyro/st_gyro_spi.c
@@ -54,7 +54,6 @@
 	{ LSM330DL_GYRO_DEV_NAME },
 	{ LSM330DLC_GYRO_DEV_NAME },
 	{ L3GD20_GYRO_DEV_NAME },
-	{ L3GD20H_GYRO_DEV_NAME },
 	{ L3G4IS_GYRO_DEV_NAME },
 	{ LSM330_GYRO_DEV_NAME },
 	{},
diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c
index f17b4e6..47a6dba 100644
--- a/drivers/iio/light/cm32181.c
+++ b/drivers/iio/light/cm32181.c
@@ -103,13 +103,13 @@
 /**
  *  cm32181_read_als_it() - Get sensor integration time (ms)
  *  @cm32181:	pointer of struct cm32181
- *  @val:	pointer of int to load the als_it value.
+ *  @val2:	pointer of int to load the als_it value.
  *
  *  Report the current integartion time by millisecond.
  *
- *  Return: IIO_VAL_INT for success, otherwise -EINVAL.
+ *  Return: IIO_VAL_INT_PLUS_MICRO for success, otherwise -EINVAL.
  */
-static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val)
+static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val2)
 {
 	u16 als_it;
 	int i;
@@ -119,8 +119,8 @@
 	als_it >>= CM32181_CMD_ALS_IT_SHIFT;
 	for (i = 0; i < ARRAY_SIZE(als_it_bits); i++) {
 		if (als_it == als_it_bits[i]) {
-			*val = als_it_value[i];
-			return IIO_VAL_INT;
+			*val2 = als_it_value[i];
+			return IIO_VAL_INT_PLUS_MICRO;
 		}
 	}
 
@@ -221,7 +221,7 @@
 		*val = cm32181->calibscale;
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_INT_TIME:
-		ret = cm32181_read_als_it(cm32181, val);
+		ret = cm32181_read_als_it(cm32181, val2);
 		return ret;
 	}
 
@@ -240,7 +240,7 @@
 		cm32181->calibscale = val;
 		return val;
 	case IIO_CHAN_INFO_INT_TIME:
-		ret = cm32181_write_als_it(cm32181, val);
+		ret = cm32181_write_als_it(cm32181, val2);
 		return ret;
 	}
 
@@ -264,7 +264,7 @@
 
 	n = ARRAY_SIZE(als_it_value);
 	for (i = 0, len = 0; i < n; i++)
-		len += sprintf(buf + len, "%d ", als_it_value[i]);
+		len += sprintf(buf + len, "0.%06u ", als_it_value[i]);
 	return len + sprintf(buf + len, "\n");
 }
 
diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c
index 0a142af..a45e074 100644
--- a/drivers/iio/light/cm36651.c
+++ b/drivers/iio/light/cm36651.c
@@ -50,10 +50,10 @@
 #define CM36651_CS_CONF2_DEFAULT_BIT	0x08
 
 /* CS_CONF3 channel integration time */
-#define CM36651_CS_IT1			0x00 /* Integration time 80000 usec */
-#define CM36651_CS_IT2			0x40 /* Integration time 160000 usec */
-#define CM36651_CS_IT3			0x80 /* Integration time 320000 usec */
-#define CM36651_CS_IT4			0xC0 /* Integration time 640000 usec */
+#define CM36651_CS_IT1			0x00 /* Integration time 80 msec */
+#define CM36651_CS_IT2			0x40 /* Integration time 160 msec */
+#define CM36651_CS_IT3			0x80 /* Integration time 320 msec */
+#define CM36651_CS_IT4			0xC0 /* Integration time 640 msec */
 
 /* PS_CONF1 command code */
 #define CM36651_PS_ENABLE		0x00
@@ -64,10 +64,10 @@
 #define CM36651_PS_PERS4		0x0C
 
 /* PS_CONF1 command code: integration time */
-#define CM36651_PS_IT1			0x00 /* Integration time 320 usec */
-#define CM36651_PS_IT2			0x10 /* Integration time 420 usec */
-#define CM36651_PS_IT3			0x20 /* Integration time 520 usec */
-#define CM36651_PS_IT4			0x30 /* Integration time 640 usec */
+#define CM36651_PS_IT1			0x00 /* Integration time 0.32 msec */
+#define CM36651_PS_IT2			0x10 /* Integration time 0.42 msec */
+#define CM36651_PS_IT3			0x20 /* Integration time 0.52 msec */
+#define CM36651_PS_IT4			0x30 /* Integration time 0.64 msec */
 
 /* PS_CONF1 command code: duty ratio */
 #define CM36651_PS_DR1			0x00 /* Duty ratio 1/80 */
@@ -93,8 +93,8 @@
 #define CM36651_CLOSE_PROXIMITY		0x32
 #define CM36651_FAR_PROXIMITY			0x33
 
-#define CM36651_CS_INT_TIME_AVAIL	"80000 160000 320000 640000"
-#define CM36651_PS_INT_TIME_AVAIL	"320 420 520 640"
+#define CM36651_CS_INT_TIME_AVAIL	"0.08 0.16 0.32 0.64"
+#define CM36651_PS_INT_TIME_AVAIL	"0.000320 0.000420 0.000520 0.000640"
 
 enum cm36651_operation_mode {
 	CM36651_LIGHT_EN,
@@ -356,30 +356,30 @@
 }
 
 static int cm36651_read_int_time(struct cm36651_data *cm36651,
-				struct iio_chan_spec const *chan, int *val)
+				struct iio_chan_spec const *chan, int *val2)
 {
 	switch (chan->type) {
 	case IIO_LIGHT:
 		if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT1)
-			*val = 80000;
+			*val2 = 80000;
 		else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT2)
-			*val = 160000;
+			*val2 = 160000;
 		else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT3)
-			*val = 320000;
+			*val2 = 320000;
 		else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT4)
-			*val = 640000;
+			*val2 = 640000;
 		else
 			return -EINVAL;
 		break;
 	case IIO_PROXIMITY:
 		if (cm36651->ps_int_time == CM36651_PS_IT1)
-			*val = 320;
+			*val2 = 320;
 		else if (cm36651->ps_int_time == CM36651_PS_IT2)
-			*val = 420;
+			*val2 = 420;
 		else if (cm36651->ps_int_time == CM36651_PS_IT3)
-			*val = 520;
+			*val2 = 520;
 		else if (cm36651->ps_int_time == CM36651_PS_IT4)
-			*val = 640;
+			*val2 = 640;
 		else
 			return -EINVAL;
 		break;
@@ -387,7 +387,7 @@
 		return -EINVAL;
 	}
 
-	return IIO_VAL_INT;
+	return IIO_VAL_INT_PLUS_MICRO;
 }
 
 static int cm36651_write_int_time(struct cm36651_data *cm36651,
@@ -459,7 +459,8 @@
 		ret = cm36651_read_channel(cm36651, chan, val);
 		break;
 	case IIO_CHAN_INFO_INT_TIME:
-		ret = cm36651_read_int_time(cm36651, chan, val);
+		*val = 0;
+		ret = cm36651_read_int_time(cm36651, chan, val2);
 		break;
 	default:
 		ret = -EINVAL;
@@ -479,7 +480,7 @@
 	int ret = -EINVAL;
 
 	if (mask == IIO_CHAN_INFO_INT_TIME) {
-		ret = cm36651_write_int_time(cm36651, chan, val);
+		ret = cm36651_write_int_time(cm36651, chan, val2);
 		if (ret < 0)
 			dev_err(&client->dev, "Integration time write failed\n");
 	}
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index e81c554..f9c12e9 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -53,8 +53,8 @@
 #include "user.h"
 
 #define DRV_NAME	MLX4_IB_DRV_NAME
-#define DRV_VERSION	"1.0"
-#define DRV_RELDATE	"April 4, 2008"
+#define DRV_VERSION	"2.2-1"
+#define DRV_RELDATE	"Feb 2014"
 
 #define MLX4_IB_FLOW_MAX_PRIO 0xFFF
 #define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index aa03e73..bf90057 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -46,8 +46,8 @@
 #include "mlx5_ib.h"
 
 #define DRIVER_NAME "mlx5_ib"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE	"June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE	"Feb 2014"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index d18d08a..8ee228e 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -492,12 +492,11 @@
 	isert_conn->state = ISER_CONN_INIT;
 	INIT_LIST_HEAD(&isert_conn->conn_accept_node);
 	init_completion(&isert_conn->conn_login_comp);
-	init_waitqueue_head(&isert_conn->conn_wait);
-	init_waitqueue_head(&isert_conn->conn_wait_comp_err);
+	init_completion(&isert_conn->conn_wait);
+	init_completion(&isert_conn->conn_wait_comp_err);
 	kref_init(&isert_conn->conn_kref);
 	kref_get(&isert_conn->conn_kref);
 	mutex_init(&isert_conn->conn_mutex);
-	mutex_init(&isert_conn->conn_comp_mutex);
 	spin_lock_init(&isert_conn->conn_lock);
 
 	cma_id->context = isert_conn;
@@ -688,11 +687,11 @@
 
 	pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
 	mutex_lock(&isert_conn->conn_mutex);
-	isert_conn->state = ISER_CONN_DOWN;
+	if (isert_conn->state == ISER_CONN_UP)
+		isert_conn->state = ISER_CONN_TERMINATING;
 
 	if (isert_conn->post_recv_buf_count == 0 &&
 	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		pr_debug("Calling wake_up(&isert_conn->conn_wait);\n");
 		mutex_unlock(&isert_conn->conn_mutex);
 		goto wake_up;
 	}
@@ -712,7 +711,7 @@
 	mutex_unlock(&isert_conn->conn_mutex);
 
 wake_up:
-	wake_up(&isert_conn->conn_wait);
+	complete(&isert_conn->conn_wait);
 	isert_put_conn(isert_conn);
 }
 
@@ -888,16 +887,17 @@
 	 * Coalesce send completion interrupts by only setting IB_SEND_SIGNALED
 	 * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls.
 	 */
-	mutex_lock(&isert_conn->conn_comp_mutex);
-	if (coalesce &&
+	mutex_lock(&isert_conn->conn_mutex);
+	if (coalesce && isert_conn->state == ISER_CONN_UP &&
 	    ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) {
+		tx_desc->llnode_active = true;
 		llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist);
-		mutex_unlock(&isert_conn->conn_comp_mutex);
+		mutex_unlock(&isert_conn->conn_mutex);
 		return;
 	}
 	isert_conn->conn_comp_batch = 0;
 	tx_desc->comp_llnode_batch = llist_del_all(&isert_conn->conn_comp_llist);
-	mutex_unlock(&isert_conn->conn_comp_mutex);
+	mutex_unlock(&isert_conn->conn_mutex);
 
 	send_wr->send_flags = IB_SEND_SIGNALED;
 }
@@ -1464,7 +1464,7 @@
 	case ISCSI_OP_SCSI_CMD:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		if (cmd->data_direction == DMA_TO_DEVICE)
@@ -1476,7 +1476,7 @@
 	case ISCSI_OP_SCSI_TMFUNC:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		transport_generic_free_cmd(&cmd->se_cmd, 0);
@@ -1486,7 +1486,7 @@
 	case ISCSI_OP_TEXT:
 		spin_lock_bh(&conn->cmd_lock);
 		if (!list_empty(&cmd->i_conn_node))
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		/*
@@ -1549,6 +1549,7 @@
 	iscsit_stop_dataout_timer(cmd);
 	device->unreg_rdma_mem(isert_cmd, isert_conn);
 	cmd->write_data_done = wr->cur_rdma_length;
+	wr->send_wr_num = 0;
 
 	pr_debug("Cmd: %p RDMA_READ comp calling execute_cmd\n", isert_cmd);
 	spin_lock_bh(&cmd->istate_lock);
@@ -1589,7 +1590,7 @@
 		pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
 		/*
 		 * Call atomic_dec(&isert_conn->post_send_buf_count)
-		 * from isert_free_conn()
+		 * from isert_wait_conn()
 		 */
 		isert_conn->logout_posted = true;
 		iscsit_logout_post_handler(cmd, cmd->conn);
@@ -1613,6 +1614,7 @@
 			  struct ib_device *ib_dev)
 {
 	struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
+	struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
 
 	if (cmd->i_state == ISTATE_SEND_TASKMGTRSP ||
 	    cmd->i_state == ISTATE_SEND_LOGOUTRSP ||
@@ -1624,7 +1626,7 @@
 		queue_work(isert_comp_wq, &isert_cmd->comp_work);
 		return;
 	}
-	atomic_dec(&isert_conn->post_send_buf_count);
+	atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	cmd->i_state = ISTATE_SENT_STATUS;
 	isert_completion_put(tx_desc, isert_cmd, ib_dev);
@@ -1662,7 +1664,7 @@
 	case ISER_IB_RDMA_READ:
 		pr_debug("isert_send_completion: Got ISER_IB_RDMA_READ:\n");
 
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 		isert_completion_rdma_read(tx_desc, isert_cmd);
 		break;
 	default:
@@ -1691,31 +1693,76 @@
 }
 
 static void
-isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
+isert_cq_drain_comp_llist(struct isert_conn *isert_conn, struct ib_device *ib_dev)
+{
+	struct llist_node *llnode;
+	struct isert_rdma_wr *wr;
+	struct iser_tx_desc *t;
+
+	mutex_lock(&isert_conn->conn_mutex);
+	llnode = llist_del_all(&isert_conn->conn_comp_llist);
+	isert_conn->conn_comp_batch = 0;
+	mutex_unlock(&isert_conn->conn_mutex);
+
+	while (llnode) {
+		t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+		llnode = llist_next(llnode);
+		wr = &t->isert_cmd->rdma_wr;
+
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
+		isert_completion_put(t, t->isert_cmd, ib_dev);
+	}
+}
+
+static void
+isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
 {
 	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+	struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+	struct llist_node *llnode = tx_desc->comp_llnode_batch;
+	struct isert_rdma_wr *wr;
+	struct iser_tx_desc *t;
 
-	if (tx_desc) {
-		struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+	while (llnode) {
+		t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+		llnode = llist_next(llnode);
+		wr = &t->isert_cmd->rdma_wr;
 
-		if (!isert_cmd)
-			isert_unmap_tx_desc(tx_desc, ib_dev);
-		else
-			isert_completion_put(tx_desc, isert_cmd, ib_dev);
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
+		isert_completion_put(t, t->isert_cmd, ib_dev);
+	}
+	tx_desc->comp_llnode_batch = NULL;
+
+	if (!isert_cmd)
+		isert_unmap_tx_desc(tx_desc, ib_dev);
+	else
+		isert_completion_put(tx_desc, isert_cmd, ib_dev);
+}
+
+static void
+isert_cq_rx_comp_err(struct isert_conn *isert_conn)
+{
+	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+	struct iscsi_conn *conn = isert_conn->conn;
+
+	if (isert_conn->post_recv_buf_count)
+		return;
+
+	isert_cq_drain_comp_llist(isert_conn, ib_dev);
+
+	if (conn->sess) {
+		target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+		target_wait_for_sess_cmds(conn->sess->se_sess);
 	}
 
-	if (isert_conn->post_recv_buf_count == 0 &&
-	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
-		pr_debug("Calling wake_up from isert_cq_comp_err\n");
+	while (atomic_read(&isert_conn->post_send_buf_count))
+		msleep(3000);
 
-		mutex_lock(&isert_conn->conn_mutex);
-		if (isert_conn->state != ISER_CONN_DOWN)
-			isert_conn->state = ISER_CONN_TERMINATING;
-		mutex_unlock(&isert_conn->conn_mutex);
+	mutex_lock(&isert_conn->conn_mutex);
+	isert_conn->state = ISER_CONN_DOWN;
+	mutex_unlock(&isert_conn->conn_mutex);
 
-		wake_up(&isert_conn->conn_wait_comp_err);
-	}
+	complete(&isert_conn->conn_wait_comp_err);
 }
 
 static void
@@ -1740,8 +1787,14 @@
 			pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n");
 			pr_debug("TX wc.status: 0x%08x\n", wc.status);
 			pr_debug("TX wc.vendor_err: 0x%08x\n", wc.vendor_err);
-			atomic_dec(&isert_conn->post_send_buf_count);
-			isert_cq_comp_err(tx_desc, isert_conn);
+
+			if (wc.wr_id != ISER_FASTREG_LI_WRID) {
+				if (tx_desc->llnode_active)
+					continue;
+
+				atomic_dec(&isert_conn->post_send_buf_count);
+				isert_cq_tx_comp_err(tx_desc, isert_conn);
+			}
 		}
 	}
 
@@ -1784,7 +1837,7 @@
 					 wc.vendor_err);
 			}
 			isert_conn->post_recv_buf_count--;
-			isert_cq_comp_err(NULL, isert_conn);
+			isert_cq_rx_comp_err(isert_conn);
 		}
 	}
 
@@ -2202,6 +2255,7 @@
 
 	if (!fr_desc->valid) {
 		memset(&inv_wr, 0, sizeof(inv_wr));
+		inv_wr.wr_id = ISER_FASTREG_LI_WRID;
 		inv_wr.opcode = IB_WR_LOCAL_INV;
 		inv_wr.ex.invalidate_rkey = fr_desc->data_mr->rkey;
 		wr = &inv_wr;
@@ -2212,6 +2266,7 @@
 
 	/* Prepare FASTREG WR */
 	memset(&fr_wr, 0, sizeof(fr_wr));
+	fr_wr.wr_id = ISER_FASTREG_LI_WRID;
 	fr_wr.opcode = IB_WR_FAST_REG_MR;
 	fr_wr.wr.fast_reg.iova_start =
 		fr_desc->data_frpl->page_list[0] + page_off;
@@ -2377,12 +2432,12 @@
 	isert_init_send_wr(isert_conn, isert_cmd,
 			   &isert_cmd->tx_desc.send_wr, true);
 
-	atomic_inc(&isert_conn->post_send_buf_count);
+	atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
 	if (rc) {
 		pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n");
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 	}
 	pr_debug("Cmd: %p posted RDMA_WRITE + Response for iSER Data READ\n",
 		 isert_cmd);
@@ -2410,12 +2465,12 @@
 		return rc;
 	}
 
-	atomic_inc(&isert_conn->post_send_buf_count);
+	atomic_add(wr->send_wr_num, &isert_conn->post_send_buf_count);
 
 	rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
 	if (rc) {
 		pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n");
-		atomic_dec(&isert_conn->post_send_buf_count);
+		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 	}
 	pr_debug("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
 		 isert_cmd);
@@ -2702,22 +2757,11 @@
 	kfree(isert_np);
 }
 
-static int isert_check_state(struct isert_conn *isert_conn, int state)
-{
-	int ret;
-
-	mutex_lock(&isert_conn->conn_mutex);
-	ret = (isert_conn->state == state);
-	mutex_unlock(&isert_conn->conn_mutex);
-
-	return ret;
-}
-
-static void isert_free_conn(struct iscsi_conn *conn)
+static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
 
-	pr_debug("isert_free_conn: Starting \n");
+	pr_debug("isert_wait_conn: Starting \n");
 	/*
 	 * Decrement post_send_buf_count for special case when called
 	 * from isert_do_control_comp() -> iscsit_logout_post_handler()
@@ -2727,38 +2771,29 @@
 		atomic_dec(&isert_conn->post_send_buf_count);
 
 	if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
-		pr_debug("Calling rdma_disconnect from isert_free_conn\n");
+		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
 		rdma_disconnect(isert_conn->conn_cm_id);
 	}
 	/*
 	 * Only wait for conn_wait_comp_err if the isert_conn made it
 	 * into full feature phase..
 	 */
-	if (isert_conn->state == ISER_CONN_UP) {
-		pr_debug("isert_free_conn: Before wait_event comp_err %d\n",
-			 isert_conn->state);
-		mutex_unlock(&isert_conn->conn_mutex);
-
-		wait_event(isert_conn->conn_wait_comp_err,
-			  (isert_check_state(isert_conn, ISER_CONN_TERMINATING)));
-
-		wait_event(isert_conn->conn_wait,
-			  (isert_check_state(isert_conn, ISER_CONN_DOWN)));
-
-		isert_put_conn(isert_conn);
-		return;
-	}
 	if (isert_conn->state == ISER_CONN_INIT) {
 		mutex_unlock(&isert_conn->conn_mutex);
-		isert_put_conn(isert_conn);
 		return;
 	}
-	pr_debug("isert_free_conn: wait_event conn_wait %d\n",
-		 isert_conn->state);
+	if (isert_conn->state == ISER_CONN_UP)
+		isert_conn->state = ISER_CONN_TERMINATING;
 	mutex_unlock(&isert_conn->conn_mutex);
 
-	wait_event(isert_conn->conn_wait,
-		  (isert_check_state(isert_conn, ISER_CONN_DOWN)));
+	wait_for_completion(&isert_conn->conn_wait_comp_err);
+
+	wait_for_completion(&isert_conn->conn_wait);
+}
+
+static void isert_free_conn(struct iscsi_conn *conn)
+{
+	struct isert_conn *isert_conn = conn->context;
 
 	isert_put_conn(isert_conn);
 }
@@ -2771,6 +2806,7 @@
 	.iscsit_setup_np	= isert_setup_np,
 	.iscsit_accept_np	= isert_accept_np,
 	.iscsit_free_np		= isert_free_np,
+	.iscsit_wait_conn	= isert_wait_conn,
 	.iscsit_free_conn	= isert_free_conn,
 	.iscsit_get_login_rx	= isert_get_login_rx,
 	.iscsit_put_login_tx	= isert_put_login_tx,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 708a069..f6ae7f5 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -6,6 +6,7 @@
 
 #define ISERT_RDMA_LISTEN_BACKLOG	10
 #define ISCSI_ISER_SG_TABLESIZE		256
+#define ISER_FASTREG_LI_WRID		0xffffffffffffffffULL
 
 enum isert_desc_type {
 	ISCSI_TX_CONTROL,
@@ -45,6 +46,7 @@
 	struct isert_cmd *isert_cmd;
 	struct llist_node *comp_llnode_batch;
 	struct llist_node comp_llnode;
+	bool		llnode_active;
 	struct ib_send_wr send_wr;
 } __packed;
 
@@ -116,8 +118,8 @@
 	struct isert_device	*conn_device;
 	struct work_struct	conn_logout_work;
 	struct mutex		conn_mutex;
-	wait_queue_head_t	conn_wait;
-	wait_queue_head_t	conn_wait_comp_err;
+	struct completion	conn_wait;
+	struct completion	conn_wait_comp_err;
 	struct kref		conn_kref;
 	struct list_head	conn_fr_pool;
 	int			conn_fr_pool_size;
@@ -126,7 +128,6 @@
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
 	struct llist_head	conn_comp_llist;
-	struct mutex		conn_comp_mutex;
 };
 
 #define ISERT_MAX_CQ 64
diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c
index 7a04f54..ef2e281 100644
--- a/drivers/input/misc/arizona-haptics.c
+++ b/drivers/input/misc/arizona-haptics.c
@@ -37,7 +37,6 @@
 						       struct arizona_haptics,
 						       work);
 	struct arizona *arizona = haptics->arizona;
-	struct mutex *dapm_mutex = &arizona->dapm->card->dapm_mutex;
 	int ret;
 
 	if (!haptics->arizona->dapm) {
@@ -67,13 +66,10 @@
 			return;
 		}
 
-		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 		ret = snd_soc_dapm_enable_pin(arizona->dapm, "HAPTICS");
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to start HAPTICS: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
@@ -81,21 +77,14 @@
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
-
-		mutex_unlock(dapm_mutex);
-
 	} else {
 		/* This disable sequence will be a noop if already enabled */
-		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 		ret = snd_soc_dapm_disable_pin(arizona->dapm, "HAPTICS");
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to disable HAPTICS: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
@@ -103,12 +92,9 @@
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
 				ret);
-			mutex_unlock(dapm_mutex);
 			return;
 		}
 
-		mutex_unlock(dapm_mutex);
-
 		ret = regmap_update_bits(arizona->regmap,
 					 ARIZONA_HAPTICS_CONTROL_1,
 					 ARIZONA_HAP_CTRL_MASK,
@@ -155,16 +141,11 @@
 static void arizona_haptics_close(struct input_dev *input)
 {
 	struct arizona_haptics *haptics = input_get_drvdata(input);
-	struct mutex *dapm_mutex = &haptics->arizona->dapm->card->dapm_mutex;
 
 	cancel_work_sync(&haptics->work);
 
-	mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 	if (haptics->arizona->dapm)
 		snd_soc_dapm_disable_pin(haptics->arizona->dapm, "HAPTICS");
-
-	mutex_unlock(dapm_mutex);
 }
 
 static int arizona_haptics_probe(struct platform_device *pdev)
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index d97fbe4..80fffba 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -354,8 +354,8 @@
 			return -ENOMEM;					\
 	}
 
-#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 600)
-#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 400)
+#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 0600)
+#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400)
 
 static int iommu_debug_register(struct device *dev, void *data)
 {
diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c
index 92c41ab..2cb474a 100644
--- a/drivers/irqchip/irq-metag-ext.c
+++ b/drivers/irqchip/irq-metag-ext.c
@@ -515,7 +515,7 @@
 	 * one cpu (the interrupt code doesn't support it), so we just
 	 * pick the first cpu we find in 'cpumask'.
 	 */
-	cpu = cpumask_any(cpumask);
+	cpu = cpumask_any_and(cpumask, cpu_online_mask);
 	thread = cpu_2_hwthread_id[cpu];
 
 	metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR2(thread)), vec_addr);
diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c
index 8e94d7a..c16c186 100644
--- a/drivers/irqchip/irq-metag.c
+++ b/drivers/irqchip/irq-metag.c
@@ -201,7 +201,7 @@
 	 * one cpu (the interrupt code doesn't support it), so we just
 	 * pick the first cpu we find in 'cpumask'.
 	 */
-	cpu = cpumask_any(cpumask);
+	cpu = cpumask_any_and(cpumask, cpu_online_mask);
 	thread = cpu_2_hwthread_id[cpu];
 
 	metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR1(thread)),
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 9a06fe8..95ad936 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -254,16 +254,6 @@
        ---help---
          Provides thin provisioning and snapshots that share a data store.
 
-config DM_DEBUG_BLOCK_STACK_TRACING
-	boolean "Keep stack trace of persistent data block lock holders"
-	depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
-	select STACKTRACE
-	---help---
-	  Enable this for messages that may help debug problems with the
-	  block manager locking used by thin provisioning and caching.
-
-	  If unsure, say N.
-
 config DM_CACHE
        tristate "Cache target (EXPERIMENTAL)"
        depends on BLK_DEV_DM
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 1e018e9..0e385e4 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -872,7 +872,7 @@
 {
 	struct mq_policy *mq = to_mq_policy(p);
 
-	kfree(mq->table);
+	vfree(mq->table);
 	epool_exit(&mq->cache_pool);
 	epool_exit(&mq->pre_cache_pool);
 	kfree(mq);
@@ -1245,7 +1245,7 @@
 
 	mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16);
 	mq->hash_bits = ffs(mq->nr_buckets) - 1;
-	mq->table = kzalloc(sizeof(*mq->table) * mq->nr_buckets, GFP_KERNEL);
+	mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets);
 	if (!mq->table)
 		goto bad_alloc_table;
 
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index ffd472e..074b9c8 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -289,6 +289,7 @@
 	bool tick:1;
 	unsigned req_nr:2;
 	struct dm_deferred_entry *all_io_entry;
+	struct dm_hook_info hook_info;
 
 	/*
 	 * writethrough fields.  These MUST remain at the end of this
@@ -297,7 +298,6 @@
 	 */
 	struct cache *cache;
 	dm_cblock_t cblock;
-	struct dm_hook_info hook_info;
 	struct dm_bio_details bio_details;
 };
 
@@ -671,15 +671,16 @@
 			   dm_cblock_t cblock)
 {
 	sector_t bi_sector = bio->bi_iter.bi_sector;
+	sector_t block = from_cblock(cblock);
 
 	bio->bi_bdev = cache->cache_dev->bdev;
 	if (!block_size_is_power_of_two(cache))
 		bio->bi_iter.bi_sector =
-			(from_cblock(cblock) * cache->sectors_per_block) +
+			(block * cache->sectors_per_block) +
 			sector_div(bi_sector, cache->sectors_per_block);
 	else
 		bio->bi_iter.bi_sector =
-			(from_cblock(cblock) << cache->sectors_per_block_shift) |
+			(block << cache->sectors_per_block_shift) |
 			(bi_sector & (cache->sectors_per_block - 1));
 }
 
@@ -978,12 +979,13 @@
 	int r;
 	struct dm_io_region o_region, c_region;
 	struct cache *cache = mg->cache;
+	sector_t cblock = from_cblock(mg->cblock);
 
 	o_region.bdev = cache->origin_dev->bdev;
 	o_region.count = cache->sectors_per_block;
 
 	c_region.bdev = cache->cache_dev->bdev;
-	c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
+	c_region.sector = cblock * cache->sectors_per_block;
 	c_region.count = cache->sectors_per_block;
 
 	if (mg->writeback || mg->demote) {
@@ -1010,13 +1012,15 @@
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 	unsigned long flags;
 
+	dm_unhook_bio(&pb->hook_info, bio);
+
 	if (err)
 		mg->err = true;
 
+	mg->requeue_holder = false;
+
 	spin_lock_irqsave(&cache->lock, flags);
 	list_add_tail(&mg->list, &cache->completed_migrations);
-	dm_unhook_bio(&pb->hook_info, bio);
-	mg->requeue_holder = false;
 	spin_unlock_irqrestore(&cache->lock, flags);
 
 	wake_worker(cache);
@@ -2461,20 +2465,18 @@
 	bool discarded_block;
 	struct dm_bio_prison_cell *cell;
 	struct policy_result lookup_result;
-	struct per_bio_data *pb;
+	struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size);
 
-	if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
+	if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) {
 		/*
 		 * This can only occur if the io goes to a partial block at
 		 * the end of the origin device.  We don't cache these.
 		 * Just remap to the origin and carry on.
 		 */
-		remap_to_origin_clear_discard(cache, bio, block);
+		remap_to_origin(cache, bio);
 		return DM_MAPIO_REMAPPED;
 	}
 
-	pb = init_per_bio_data(bio, pb_data_size);
-
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
 		defer_bio(cache, bio);
 		return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index b2b8a10..3842ac7 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -201,29 +201,28 @@
 /*
  * Functions for getting the pages from a bvec.
  */
-static void bio_get_page(struct dpages *dp,
-		  struct page **p, unsigned long *len, unsigned *offset)
+static void bio_get_page(struct dpages *dp, struct page **p,
+			 unsigned long *len, unsigned *offset)
 {
-	struct bio *bio = dp->context_ptr;
-	struct bio_vec bvec = bio_iovec(bio);
-	*p = bvec.bv_page;
-	*len = bvec.bv_len;
-	*offset = bvec.bv_offset;
+	struct bio_vec *bvec = dp->context_ptr;
+	*p = bvec->bv_page;
+	*len = bvec->bv_len - dp->context_u;
+	*offset = bvec->bv_offset + dp->context_u;
 }
 
 static void bio_next_page(struct dpages *dp)
 {
-	struct bio *bio = dp->context_ptr;
-	struct bio_vec bvec = bio_iovec(bio);
-
-	bio_advance(bio, bvec.bv_len);
+	struct bio_vec *bvec = dp->context_ptr;
+	dp->context_ptr = bvec + 1;
+	dp->context_u = 0;
 }
 
 static void bio_dp_init(struct dpages *dp, struct bio *bio)
 {
 	dp->get_page = bio_get_page;
 	dp->next_page = bio_next_page;
-	dp->context_ptr = bio;
+	dp->context_ptr = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+	dp->context_u = bio->bi_iter.bi_bvec_done;
 }
 
 /*
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6eb9dc9..422a9fd 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1626,8 +1626,11 @@
 	/*
 	 * Only pass ioctls through if the device sizes match exactly.
 	 */
-	if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
-		r = scsi_verify_blk_ioctl(NULL, cmd);
+	if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
+		int err = scsi_verify_blk_ioctl(NULL, cmd);
+		if (err)
+			r = err;
+	}
 
 	if (r == -ENOTCONN && !fatal_signal_pending(current))
 		queue_work(kmultipathd, &m->process_queued_ios);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index f284e0b..7dfdb5c 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1244,6 +1244,9 @@
 
 			dm_bio_restore(bd, bio);
 			bio_record->details.bi_bdev = NULL;
+
+			atomic_inc(&bio->bi_remaining);
+
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
 		}
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index afc3d01..d6e8817 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -546,6 +546,9 @@
 		r = insert_exceptions(ps, area, callback, callback_context,
 				      &full);
 
+		if (!full)
+			memcpy(ps->area, area, ps->store->chunk_size << SECTOR_SHIFT);
+
 		dm_bufio_release(bp);
 
 		dm_bufio_forget(client, chunk);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 7da3476..fb9efc8 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -76,7 +76,7 @@
 
 #define THIN_SUPERBLOCK_MAGIC 27022010
 #define THIN_SUPERBLOCK_LOCATION 0
-#define THIN_VERSION 1
+#define THIN_VERSION 2
 #define THIN_METADATA_CACHE_SIZE 64
 #define SECTOR_TO_BLOCK_SHIFT 3
 
@@ -483,7 +483,7 @@
 
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
-	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE);
 	disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT);
 	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
 
@@ -651,7 +651,7 @@
 {
 	int r;
 
-	pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE,
+	pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
 					  THIN_METADATA_CACHE_SIZE,
 					  THIN_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(pmd->bm)) {
@@ -1489,6 +1489,23 @@
 	return r;
 }
 
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd)
+{
+	bool r = false;
+	struct dm_thin_device *td, *tmp;
+
+	down_read(&pmd->root_lock);
+	list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+		if (td->changed) {
+			r = td->changed;
+			break;
+		}
+	}
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_aborted_changes(struct dm_thin_device *td)
 {
 	bool r;
@@ -1738,3 +1755,38 @@
 
 	return r;
 }
+
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
+{
+	int r;
+	struct dm_block *sblock;
+	struct thin_disk_superblock *disk_super;
+
+	down_write(&pmd->root_lock);
+	pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;
+
+	r = superblock_lock(pmd, &sblock);
+	if (r) {
+		DMERR("couldn't read superblock");
+		goto out;
+	}
+
+	disk_super = dm_block_data(sblock);
+	disk_super->flags = cpu_to_le32(pmd->flags);
+
+	dm_bm_unlock(sblock);
+out:
+	up_write(&pmd->root_lock);
+	return r;
+}
+
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
+{
+	bool needs_check;
+
+	down_read(&pmd->root_lock);
+	needs_check = pmd->flags & THIN_METADATA_NEEDS_CHECK_FLAG;
+	up_read(&pmd->root_lock);
+
+	return needs_check;
+}
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 9a36856..e3c857d 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -9,16 +9,14 @@
 
 #include "persistent-data/dm-block-manager.h"
 #include "persistent-data/dm-space-map.h"
+#include "persistent-data/dm-space-map-metadata.h"
 
-#define THIN_METADATA_BLOCK_SIZE 4096
+#define THIN_METADATA_BLOCK_SIZE DM_SM_METADATA_BLOCK_SIZE
 
 /*
  * The metadata device is currently limited in size.
- *
- * We have one block of index, which can hold 255 index entries.  Each
- * index entry contains allocation info about 16k metadata blocks.
  */
-#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+#define THIN_METADATA_MAX_SECTORS DM_SM_METADATA_MAX_SECTORS
 
 /*
  * A metadata device larger than 16GB triggers a warning.
@@ -27,6 +25,11 @@
 
 /*----------------------------------------------------------------*/
 
+/*
+ * Thin metadata superblock flags.
+ */
+#define THIN_METADATA_NEEDS_CHECK_FLAG (1 << 0)
+
 struct dm_pool_metadata;
 struct dm_thin_device;
 
@@ -161,6 +164,8 @@
  */
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td);
 
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd);
+
 bool dm_thin_aborted_changes(struct dm_thin_device *td);
 
 int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
@@ -202,6 +207,12 @@
 					dm_sm_threshold_fn fn,
 					void *context);
 
+/*
+ * Updates the superblock immediately.
+ */
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd);
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd);
+
 /*----------------------------------------------------------------*/
 
 #endif
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index faaf944..be70d38 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -130,10 +130,11 @@
 struct dm_thin_new_mapping;
 
 /*
- * The pool runs in 3 modes.  Ordered in degraded order for comparisons.
+ * The pool runs in 4 modes.  Ordered in degraded order for comparisons.
  */
 enum pool_mode {
 	PM_WRITE,		/* metadata may be changed */
+	PM_OUT_OF_DATA_SPACE,	/* metadata may be changed, though data may not be allocated */
 	PM_READ_ONLY,		/* metadata may not be changed */
 	PM_FAIL,		/* all I/O fails */
 };
@@ -198,7 +199,6 @@
 };
 
 static enum pool_mode get_pool_mode(struct pool *pool);
-static void out_of_data_space(struct pool *pool);
 static void metadata_operation_failed(struct pool *pool, const char *op, int r);
 
 /*
@@ -226,6 +226,7 @@
 
 	struct pool *pool;
 	struct dm_thin_device *td;
+	bool requeue_mode:1;
 };
 
 /*----------------------------------------------------------------*/
@@ -369,14 +370,18 @@
 	struct dm_thin_new_mapping *overwrite_mapping;
 };
 
-static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master)
+static void requeue_bio_list(struct thin_c *tc, struct bio_list *master)
 {
 	struct bio *bio;
 	struct bio_list bios;
+	unsigned long flags;
 
 	bio_list_init(&bios);
+
+	spin_lock_irqsave(&tc->pool->lock, flags);
 	bio_list_merge(&bios, master);
 	bio_list_init(master);
+	spin_unlock_irqrestore(&tc->pool->lock, flags);
 
 	while ((bio = bio_list_pop(&bios))) {
 		struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -391,12 +396,26 @@
 static void requeue_io(struct thin_c *tc)
 {
 	struct pool *pool = tc->pool;
+
+	requeue_bio_list(tc, &pool->deferred_bios);
+	requeue_bio_list(tc, &pool->retry_on_resume_list);
+}
+
+static void error_retry_list(struct pool *pool)
+{
+	struct bio *bio;
 	unsigned long flags;
+	struct bio_list bios;
+
+	bio_list_init(&bios);
 
 	spin_lock_irqsave(&pool->lock, flags);
-	__requeue_bio_list(tc, &pool->deferred_bios);
-	__requeue_bio_list(tc, &pool->retry_on_resume_list);
+	bio_list_merge(&bios, &pool->retry_on_resume_list);
+	bio_list_init(&pool->retry_on_resume_list);
 	spin_unlock_irqrestore(&pool->lock, flags);
+
+	while ((bio = bio_list_pop(&bios)))
+		bio_io_error(bio);
 }
 
 /*
@@ -925,13 +944,15 @@
 	}
 }
 
+static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+
 static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 {
 	int r;
 	dm_block_t free_blocks;
 	struct pool *pool = tc->pool;
 
-	if (get_pool_mode(pool) != PM_WRITE)
+	if (WARN_ON(get_pool_mode(pool) != PM_WRITE))
 		return -EINVAL;
 
 	r = dm_pool_get_free_block_count(pool->pmd, &free_blocks);
@@ -958,7 +979,7 @@
 		}
 
 		if (!free_blocks) {
-			out_of_data_space(pool);
+			set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
 			return -ENOSPC;
 		}
 	}
@@ -988,15 +1009,32 @@
 	spin_unlock_irqrestore(&pool->lock, flags);
 }
 
+static bool should_error_unserviceable_bio(struct pool *pool)
+{
+	enum pool_mode m = get_pool_mode(pool);
+
+	switch (m) {
+	case PM_WRITE:
+		/* Shouldn't get here */
+		DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode");
+		return true;
+
+	case PM_OUT_OF_DATA_SPACE:
+		return pool->pf.error_if_no_space;
+
+	case PM_READ_ONLY:
+	case PM_FAIL:
+		return true;
+	default:
+		/* Shouldn't get here */
+		DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode");
+		return true;
+	}
+}
+
 static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
 {
-	/*
-	 * When pool is read-only, no cell locking is needed because
-	 * nothing is changing.
-	 */
-	WARN_ON_ONCE(get_pool_mode(pool) != PM_READ_ONLY);
-
-	if (pool->pf.error_if_no_space)
+	if (should_error_unserviceable_bio(pool))
 		bio_io_error(bio);
 	else
 		retry_on_resume(bio);
@@ -1007,11 +1045,20 @@
 	struct bio *bio;
 	struct bio_list bios;
 
+	if (should_error_unserviceable_bio(pool)) {
+		cell_error(pool, cell);
+		return;
+	}
+
 	bio_list_init(&bios);
 	cell_release(pool, cell, &bios);
 
-	while ((bio = bio_list_pop(&bios)))
-		handle_unserviceable_bio(pool, bio);
+	if (should_error_unserviceable_bio(pool))
+		while ((bio = bio_list_pop(&bios)))
+			bio_io_error(bio);
+	else
+		while ((bio = bio_list_pop(&bios)))
+			retry_on_resume(bio);
 }
 
 static void process_discard(struct thin_c *tc, struct bio *bio)
@@ -1296,6 +1343,11 @@
 	}
 }
 
+static void process_bio_success(struct thin_c *tc, struct bio *bio)
+{
+	bio_endio(bio, 0);
+}
+
 static void process_bio_fail(struct thin_c *tc, struct bio *bio)
 {
 	bio_io_error(bio);
@@ -1328,6 +1380,11 @@
 		struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 		struct thin_c *tc = h->tc;
 
+		if (tc->requeue_mode) {
+			bio_endio(bio, DM_ENDIO_REQUEUE);
+			continue;
+		}
+
 		/*
 		 * If we've got no free new_mapping structs, and processing
 		 * this bio might require one, we pause until there are some
@@ -1357,7 +1414,8 @@
 	bio_list_init(&pool->deferred_flush_bios);
 	spin_unlock_irqrestore(&pool->lock, flags);
 
-	if (bio_list_empty(&bios) && !need_commit_due_to_time(pool))
+	if (bio_list_empty(&bios) &&
+	    !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
 		return;
 
 	if (commit(pool)) {
@@ -1393,51 +1451,134 @@
 
 /*----------------------------------------------------------------*/
 
+struct noflush_work {
+	struct work_struct worker;
+	struct thin_c *tc;
+
+	atomic_t complete;
+	wait_queue_head_t wait;
+};
+
+static void complete_noflush_work(struct noflush_work *w)
+{
+	atomic_set(&w->complete, 1);
+	wake_up(&w->wait);
+}
+
+static void do_noflush_start(struct work_struct *ws)
+{
+	struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+	w->tc->requeue_mode = true;
+	requeue_io(w->tc);
+	complete_noflush_work(w);
+}
+
+static void do_noflush_stop(struct work_struct *ws)
+{
+	struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+	w->tc->requeue_mode = false;
+	complete_noflush_work(w);
+}
+
+static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
+{
+	struct noflush_work w;
+
+	INIT_WORK(&w.worker, fn);
+	w.tc = tc;
+	atomic_set(&w.complete, 0);
+	init_waitqueue_head(&w.wait);
+
+	queue_work(tc->pool->wq, &w.worker);
+
+	wait_event(w.wait, atomic_read(&w.complete));
+}
+
+/*----------------------------------------------------------------*/
+
 static enum pool_mode get_pool_mode(struct pool *pool)
 {
 	return pool->pf.mode;
 }
 
+static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
+{
+	dm_table_event(pool->ti->table);
+	DMINFO("%s: switching pool to %s mode",
+	       dm_device_name(pool->pool_md), new_mode);
+}
+
 static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 {
-	int r;
-	enum pool_mode old_mode = pool->pf.mode;
+	struct pool_c *pt = pool->ti->private;
+	bool needs_check = dm_pool_metadata_needs_check(pool->pmd);
+	enum pool_mode old_mode = get_pool_mode(pool);
+
+	/*
+	 * Never allow the pool to transition to PM_WRITE mode if user
+	 * intervention is required to verify metadata and data consistency.
+	 */
+	if (new_mode == PM_WRITE && needs_check) {
+		DMERR("%s: unable to switch pool to write mode until repaired.",
+		      dm_device_name(pool->pool_md));
+		if (old_mode != new_mode)
+			new_mode = old_mode;
+		else
+			new_mode = PM_READ_ONLY;
+	}
+	/*
+	 * If we were in PM_FAIL mode, rollback of metadata failed.  We're
+	 * not going to recover without a thin_repair.	So we never let the
+	 * pool move out of the old mode.
+	 */
+	if (old_mode == PM_FAIL)
+		new_mode = old_mode;
 
 	switch (new_mode) {
 	case PM_FAIL:
 		if (old_mode != new_mode)
-			DMERR("%s: switching pool to failure mode",
-			      dm_device_name(pool->pool_md));
+			notify_of_pool_mode_change(pool, "failure");
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_fail;
 		pool->process_discard = process_bio_fail;
 		pool->process_prepared_mapping = process_prepared_mapping_fail;
 		pool->process_prepared_discard = process_prepared_discard_fail;
+
+		error_retry_list(pool);
 		break;
 
 	case PM_READ_ONLY:
 		if (old_mode != new_mode)
-			DMERR("%s: switching pool to read-only mode",
-			      dm_device_name(pool->pool_md));
-		r = dm_pool_abort_metadata(pool->pmd);
-		if (r) {
-			DMERR("%s: aborting transaction failed",
-			      dm_device_name(pool->pool_md));
-			new_mode = PM_FAIL;
-			set_pool_mode(pool, new_mode);
-		} else {
-			dm_pool_metadata_read_only(pool->pmd);
-			pool->process_bio = process_bio_read_only;
-			pool->process_discard = process_discard;
-			pool->process_prepared_mapping = process_prepared_mapping_fail;
-			pool->process_prepared_discard = process_prepared_discard_passdown;
-		}
+			notify_of_pool_mode_change(pool, "read-only");
+		dm_pool_metadata_read_only(pool->pmd);
+		pool->process_bio = process_bio_read_only;
+		pool->process_discard = process_bio_success;
+		pool->process_prepared_mapping = process_prepared_mapping_fail;
+		pool->process_prepared_discard = process_prepared_discard_passdown;
+
+		error_retry_list(pool);
+		break;
+
+	case PM_OUT_OF_DATA_SPACE:
+		/*
+		 * Ideally we'd never hit this state; the low water mark
+		 * would trigger userland to extend the pool before we
+		 * completely run out of data space.  However, many small
+		 * IOs to unprovisioned space can consume data space at an
+		 * alarming rate.  Adjust your low water mark if you're
+		 * frequently seeing this mode.
+		 */
+		if (old_mode != new_mode)
+			notify_of_pool_mode_change(pool, "out-of-data-space");
+		pool->process_bio = process_bio_read_only;
+		pool->process_discard = process_discard;
+		pool->process_prepared_mapping = process_prepared_mapping;
+		pool->process_prepared_discard = process_prepared_discard_passdown;
 		break;
 
 	case PM_WRITE:
 		if (old_mode != new_mode)
-			DMINFO("%s: switching pool to write mode",
-			       dm_device_name(pool->pool_md));
+			notify_of_pool_mode_change(pool, "write");
 		dm_pool_metadata_read_write(pool->pmd);
 		pool->process_bio = process_bio;
 		pool->process_discard = process_discard;
@@ -1447,32 +1588,35 @@
 	}
 
 	pool->pf.mode = new_mode;
+	/*
+	 * The pool mode may have changed, sync it so bind_control_target()
+	 * doesn't cause an unexpected mode transition on resume.
+	 */
+	pt->adjusted_pf.mode = new_mode;
 }
 
-/*
- * Rather than calling set_pool_mode directly, use these which describe the
- * reason for mode degradation.
- */
-static void out_of_data_space(struct pool *pool)
+static void abort_transaction(struct pool *pool)
 {
-	DMERR_LIMIT("%s: no free data space available.",
-		    dm_device_name(pool->pool_md));
-	set_pool_mode(pool, PM_READ_ONLY);
+	const char *dev_name = dm_device_name(pool->pool_md);
+
+	DMERR_LIMIT("%s: aborting current metadata transaction", dev_name);
+	if (dm_pool_abort_metadata(pool->pmd)) {
+		DMERR("%s: failed to abort metadata transaction", dev_name);
+		set_pool_mode(pool, PM_FAIL);
+	}
+
+	if (dm_pool_metadata_set_needs_check(pool->pmd)) {
+		DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name);
+		set_pool_mode(pool, PM_FAIL);
+	}
 }
 
 static void metadata_operation_failed(struct pool *pool, const char *op, int r)
 {
-	dm_block_t free_blocks;
-
 	DMERR_LIMIT("%s: metadata operation '%s' failed: error = %d",
 		    dm_device_name(pool->pool_md), op, r);
 
-	if (r == -ENOSPC &&
-	    !dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks) &&
-	    !free_blocks)
-		DMERR_LIMIT("%s: no free metadata space available.",
-			    dm_device_name(pool->pool_md));
-
+	abort_transaction(pool);
 	set_pool_mode(pool, PM_READ_ONLY);
 }
 
@@ -1523,6 +1667,11 @@
 
 	thin_hook_bio(tc, bio);
 
+	if (tc->requeue_mode) {
+		bio_endio(bio, DM_ENDIO_REQUEUE);
+		return DM_MAPIO_SUBMITTED;
+	}
+
 	if (get_pool_mode(tc->pool) == PM_FAIL) {
 		bio_io_error(bio);
 		return DM_MAPIO_SUBMITTED;
@@ -1686,7 +1835,7 @@
 	/*
 	 * We want to make sure that a pool in PM_FAIL mode is never upgraded.
 	 */
-	enum pool_mode old_mode = pool->pf.mode;
+	enum pool_mode old_mode = get_pool_mode(pool);
 	enum pool_mode new_mode = pt->adjusted_pf.mode;
 
 	/*
@@ -1700,16 +1849,6 @@
 	pool->pf = pt->adjusted_pf;
 	pool->low_water_blocks = pt->low_water_blocks;
 
-	/*
-	 * If we were in PM_FAIL mode, rollback of metadata failed.  We're
-	 * not going to recover without a thin_repair.  So we never let the
-	 * pool move out of the old mode.  On the other hand a PM_READ_ONLY
-	 * may have been due to a lack of metadata or data space, and may
-	 * now work (ie. if the underlying devices have been resized).
-	 */
-	if (old_mode == PM_FAIL)
-		new_mode = old_mode;
-
 	set_pool_mode(pool, new_mode);
 
 	return 0;
@@ -1999,16 +2138,27 @@
 	dm_table_event(pool->ti->table);
 }
 
-static sector_t get_metadata_dev_size(struct block_device *bdev)
+static sector_t get_dev_size(struct block_device *bdev)
 {
-	sector_t metadata_dev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+	return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+}
+
+static void warn_if_metadata_device_too_big(struct block_device *bdev)
+{
+	sector_t metadata_dev_size = get_dev_size(bdev);
 	char buffer[BDEVNAME_SIZE];
 
-	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) {
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING)
 		DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
 		       bdevname(bdev, buffer), THIN_METADATA_MAX_SECTORS);
-		metadata_dev_size = THIN_METADATA_MAX_SECTORS_WARNING;
-	}
+}
+
+static sector_t get_metadata_dev_size(struct block_device *bdev)
+{
+	sector_t metadata_dev_size = get_dev_size(bdev);
+
+	if (metadata_dev_size > THIN_METADATA_MAX_SECTORS)
+		metadata_dev_size = THIN_METADATA_MAX_SECTORS;
 
 	return metadata_dev_size;
 }
@@ -2017,7 +2167,7 @@
 {
 	sector_t metadata_dev_size = get_metadata_dev_size(bdev);
 
-	sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+	sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE);
 
 	return metadata_dev_size;
 }
@@ -2095,12 +2245,7 @@
 		ti->error = "Error opening metadata block device";
 		goto out_unlock;
 	}
-
-	/*
-	 * Run for the side-effect of possibly issuing a warning if the
-	 * device is too big.
-	 */
-	(void) get_metadata_dev_size(metadata_dev->bdev);
+	warn_if_metadata_device_too_big(metadata_dev->bdev);
 
 	r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
 	if (r) {
@@ -2246,6 +2391,12 @@
 		return -EINVAL;
 
 	} else if (data_size > sb_data_size) {
+		if (dm_pool_metadata_needs_check(pool->pmd)) {
+			DMERR("%s: unable to grow the data device until repaired.",
+			      dm_device_name(pool->pool_md));
+			return 0;
+		}
+
 		if (sb_data_size)
 			DMINFO("%s: growing the data device from %llu to %llu blocks",
 			       dm_device_name(pool->pool_md),
@@ -2287,6 +2438,13 @@
 		return -EINVAL;
 
 	} else if (metadata_dev_size > sb_metadata_dev_size) {
+		if (dm_pool_metadata_needs_check(pool->pmd)) {
+			DMERR("%s: unable to grow the metadata device until repaired.",
+			      dm_device_name(pool->pool_md));
+			return 0;
+		}
+
+		warn_if_metadata_device_too_big(pool->md_dev);
 		DMINFO("%s: growing the metadata device from %llu to %llu blocks",
 		       dm_device_name(pool->pool_md),
 		       sb_metadata_dev_size, metadata_dev_size);
@@ -2673,7 +2831,9 @@
 		else
 			DMEMIT("- ");
 
-		if (pool->pf.mode == PM_READ_ONLY)
+		if (pool->pf.mode == PM_OUT_OF_DATA_SPACE)
+			DMEMIT("out_of_data_space ");
+		else if (pool->pf.mode == PM_READ_ONLY)
 			DMEMIT("ro ");
 		else
 			DMEMIT("rw ");
@@ -2787,7 +2947,7 @@
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 10, 0},
+	.version = {1, 11, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -2894,6 +3054,7 @@
 
 	if (get_pool_mode(tc->pool) == PM_FAIL) {
 		ti->error = "Couldn't open thin device, Pool is in fail mode";
+		r = -EINVAL;
 		goto bad_thin_open;
 	}
 
@@ -2905,7 +3066,7 @@
 
 	r = dm_set_target_max_io_len(ti, tc->pool->sectors_per_block);
 	if (r)
-		goto bad_thin_open;
+		goto bad_target_max_io_len;
 
 	ti->num_flush_bios = 1;
 	ti->flush_supported = true;
@@ -2926,6 +3087,8 @@
 
 	return 0;
 
+bad_target_max_io_len:
+	dm_pool_close_thin_device(tc->td);
 bad_thin_open:
 	__pool_dec(tc->pool);
 bad_pool_lookup:
@@ -2986,10 +3149,23 @@
 	return 0;
 }
 
+static void thin_presuspend(struct dm_target *ti)
+{
+	struct thin_c *tc = ti->private;
+
+	if (dm_noflush_suspending(ti))
+		noflush_work(tc, do_noflush_start);
+}
+
 static void thin_postsuspend(struct dm_target *ti)
 {
-	if (dm_noflush_suspending(ti))
-		requeue_io((struct thin_c *)ti->private);
+	struct thin_c *tc = ti->private;
+
+	/*
+	 * The dm_noflush_suspending flag has been cleared by now, so
+	 * unfortunately we must always run this.
+	 */
+	noflush_work(tc, do_noflush_stop);
 }
 
 /*
@@ -3074,12 +3250,13 @@
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 10, 0},
+	.version = {1, 11, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
 	.map = thin_map,
 	.end_io = thin_endio,
+	.presuspend = thin_presuspend,
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
 	.iterate_devices = thin_iterate_devices,
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
index 19b2687..0c2dec7 100644
--- a/drivers/md/persistent-data/Kconfig
+++ b/drivers/md/persistent-data/Kconfig
@@ -6,3 +6,13 @@
        ---help---
 	 Library providing immutable on-disk data structure support for
 	 device-mapper targets such as the thin provisioning target.
+
+config DM_DEBUG_BLOCK_STACK_TRACING
+       boolean "Keep stack trace of persistent data block lock holders"
+       depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
+       select STACKTRACE
+       ---help---
+	 Enable this for messages that may help debug problems with the
+	 block manager locking used by thin provisioning and caching.
+
+	 If unsure, say N.
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 536782e..786b689 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -91,6 +91,69 @@
 	dm_block_t block;
 };
 
+struct bop_ring_buffer {
+	unsigned begin;
+	unsigned end;
+	struct block_op bops[MAX_RECURSIVE_ALLOCATIONS + 1];
+};
+
+static void brb_init(struct bop_ring_buffer *brb)
+{
+	brb->begin = 0;
+	brb->end = 0;
+}
+
+static bool brb_empty(struct bop_ring_buffer *brb)
+{
+	return brb->begin == brb->end;
+}
+
+static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old)
+{
+	unsigned r = old + 1;
+	return (r >= (sizeof(brb->bops) / sizeof(*brb->bops))) ? 0 : r;
+}
+
+static int brb_push(struct bop_ring_buffer *brb,
+		    enum block_op_type type, dm_block_t b)
+{
+	struct block_op *bop;
+	unsigned next = brb_next(brb, brb->end);
+
+	/*
+	 * We don't allow the last bop to be filled, this way we can
+	 * differentiate between full and empty.
+	 */
+	if (next == brb->begin)
+		return -ENOMEM;
+
+	bop = brb->bops + brb->end;
+	bop->type = type;
+	bop->block = b;
+
+	brb->end = next;
+
+	return 0;
+}
+
+static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
+{
+	struct block_op *bop;
+
+	if (brb_empty(brb))
+		return -ENODATA;
+
+	bop = brb->bops + brb->begin;
+	result->type = bop->type;
+	result->block = bop->block;
+
+	brb->begin = brb_next(brb, brb->begin);
+
+	return 0;
+}
+
+/*----------------------------------------------------------------*/
+
 struct sm_metadata {
 	struct dm_space_map sm;
 
@@ -101,25 +164,20 @@
 
 	unsigned recursion_count;
 	unsigned allocated_this_transaction;
-	unsigned nr_uncommitted;
-	struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS];
+	struct bop_ring_buffer uncommitted;
 
 	struct threshold threshold;
 };
 
 static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b)
 {
-	struct block_op *op;
+	int r = brb_push(&smm->uncommitted, type, b);
 
-	if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) {
+	if (r) {
 		DMERR("too many recursive allocations");
 		return -ENOMEM;
 	}
 
-	op = smm->uncommitted + smm->nr_uncommitted++;
-	op->type = type;
-	op->block = b;
-
 	return 0;
 }
 
@@ -158,11 +216,17 @@
 		return -ENOMEM;
 	}
 
-	if (smm->recursion_count == 1 && smm->nr_uncommitted) {
-		while (smm->nr_uncommitted && !r) {
-			smm->nr_uncommitted--;
-			r = commit_bop(smm, smm->uncommitted +
-				       smm->nr_uncommitted);
+	if (smm->recursion_count == 1) {
+		while (!brb_empty(&smm->uncommitted)) {
+			struct block_op bop;
+
+			r = brb_pop(&smm->uncommitted, &bop);
+			if (r) {
+				DMERR("bug in bop ring buffer");
+				break;
+			}
+
+			r = commit_bop(smm, &bop);
 			if (r)
 				break;
 		}
@@ -217,7 +281,8 @@
 static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
 				 uint32_t *result)
 {
-	int r, i;
+	int r;
+	unsigned i;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 	unsigned adjustment = 0;
 
@@ -225,8 +290,10 @@
 	 * We may have some uncommitted adjustments to add.  This list
 	 * should always be really short.
 	 */
-	for (i = 0; i < smm->nr_uncommitted; i++) {
-		struct block_op *op = smm->uncommitted + i;
+	for (i = smm->uncommitted.begin;
+	     i != smm->uncommitted.end;
+	     i = brb_next(&smm->uncommitted, i)) {
+		struct block_op *op = smm->uncommitted.bops + i;
 
 		if (op->block != b)
 			continue;
@@ -254,7 +321,8 @@
 static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm,
 					      dm_block_t b, int *result)
 {
-	int r, i, adjustment = 0;
+	int r, adjustment = 0;
+	unsigned i;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 	uint32_t rc;
 
@@ -262,8 +330,11 @@
 	 * We may have some uncommitted adjustments to add.  This list
 	 * should always be really short.
 	 */
-	for (i = 0; i < smm->nr_uncommitted; i++) {
-		struct block_op *op = smm->uncommitted + i;
+	for (i = smm->uncommitted.begin;
+	     i != smm->uncommitted.end;
+	     i = brb_next(&smm->uncommitted, i)) {
+
+		struct block_op *op = smm->uncommitted.bops + i;
 
 		if (op->block != b)
 			continue;
@@ -671,7 +742,7 @@
 	smm->begin = superblock + 1;
 	smm->recursion_count = 0;
 	smm->allocated_this_transaction = 0;
-	smm->nr_uncommitted = 0;
+	brb_init(&smm->uncommitted);
 	threshold_init(&smm->threshold);
 
 	memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
@@ -680,6 +751,8 @@
 	if (r)
 		return r;
 
+	if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
+		nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
 	r = sm_ll_extend(&smm->ll, nr_blocks);
 	if (r)
 		return r;
@@ -713,7 +786,7 @@
 	smm->begin = 0;
 	smm->recursion_count = 0;
 	smm->allocated_this_transaction = 0;
-	smm->nr_uncommitted = 0;
+	brb_init(&smm->uncommitted);
 	threshold_init(&smm->threshold);
 
 	memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll));
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h
index 39bba08..64df923 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.h
+++ b/drivers/md/persistent-data/dm-space-map-metadata.h
@@ -9,6 +9,17 @@
 
 #include "dm-transaction-manager.h"
 
+#define DM_SM_METADATA_BLOCK_SIZE (4096 >> SECTOR_SHIFT)
+
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries.  Each
+ * index entry contains allocation info about ~16k metadata blocks.
+ */
+#define DM_SM_METADATA_MAX_BLOCKS (255 * ((1 << 14) - 64))
+#define DM_SM_METADATA_MAX_SECTORS (DM_SM_METADATA_MAX_BLOCKS * DM_SM_METADATA_BLOCK_SIZE)
+
 /*
  * Unfortunately we have to use two-phase construction due to the cycle
  * between the tm and sm.
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index b9e2000..95c8944 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -240,7 +240,7 @@
 
 	nid = cpu_to_node(cpu);
 	page = alloc_pages_exact_node(nid,
-				      GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				      GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				      pg_order);
 	if (page == NULL) {
 		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 59eba5d..9715a7b 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1584,7 +1584,7 @@
 			}
 
 			if (mtd->ecc_stats.failed - ecc_failures) {
-				if (retry_mode + 1 <= chip->read_retries) {
+				if (retry_mode + 1 < chip->read_retries) {
 					retry_mode++;
 					ret = nand_setup_read_retry(mtd,
 							retry_mode);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index ef4190a..bf642ce 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1633,6 +1633,7 @@
 	int				i;
 	dma_cap_mask_t			mask;
 	unsigned			sig;
+	unsigned			oob_index;
 	struct resource			*res;
 	struct mtd_part_parser_data	ppdata = {};
 
@@ -1826,11 +1827,14 @@
 							(mtd->writesize /
 							nand_chip->ecc.size);
 		if (nand_chip->options & NAND_BUSWIDTH_16)
-			ecclayout->eccpos[0]	= BADBLOCK_MARKER_LENGTH;
+			oob_index		= BADBLOCK_MARKER_LENGTH;
 		else
-			ecclayout->eccpos[0]	= 1;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+			oob_index		= 1;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* no reserved-marker in ecclayout for this ecc-scheme */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
@@ -1847,9 +1851,15 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
+			ecclayout->eccpos[i] = oob_index;
+			if (((i + 1) % nand_chip->ecc.bytes) == 0)
+				oob_index++;
+		}
+		/* include reserved-marker in ecclayout->oobfree calculation */
+		ecclayout->oobfree->offset	= 1 +
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		/* software bch library is used for locating errors */
 		nand_chip->ecc.priv		= nand_bch_init(mtd,
 							nand_chip->ecc.size,
@@ -1883,9 +1893,12 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* reserved marker already included in ecclayout->eccbytes */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		/* This ECC scheme requires ELM H/W block */
 		if (is_elm_present(info, pdata->elm_of_node, BCH4_ECC) < 0) {
 			pr_err("nand: error: could not initialize ELM\n");
@@ -1913,9 +1926,15 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
+			ecclayout->eccpos[i] = oob_index;
+			if (((i + 1) % nand_chip->ecc.bytes) == 0)
+				oob_index++;
+		}
+		/* include reserved-marker in ecclayout->oobfree calculation */
+		ecclayout->oobfree->offset	= 1 +
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		/* software bch library is used for locating errors */
 		nand_chip->ecc.priv		= nand_bch_init(mtd,
 							nand_chip->ecc.size,
@@ -1956,9 +1975,12 @@
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
 							nand_chip->ecc.size);
-		ecclayout->eccpos[0]		= BADBLOCK_MARKER_LENGTH;
-		ecclayout->oobfree->offset	= ecclayout->eccpos[0] +
-							ecclayout->eccbytes;
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* reserved marker already included in ecclayout->eccbytes */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
 #else
 		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
@@ -1972,11 +1994,8 @@
 		goto return_error;
 	}
 
-	/* populate remaining ECC layout data */
-	ecclayout->oobfree->length = mtd->oobsize - (BADBLOCK_MARKER_LENGTH +
-							ecclayout->eccbytes);
-	for (i = 1; i < ecclayout->eccbytes; i++)
-		ecclayout->eccpos[i] = ecclayout->eccpos[0] + i;
+	/* all OOB bytes from oobfree->offset till end off OOB are free */
+	ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset;
 	/* check if NAND device's OOB is enough to store ECC signatures */
 	if (mtd->oobsize < (ecclayout->eccbytes + BADBLOCK_MARKER_LENGTH)) {
 		pr_err("not enough OOB bytes required = %d, available=%d\n",
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index ead8613..c5dad65 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -463,8 +463,8 @@
 				}
 			}
 			if (found_orphan) {
-				kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 				list_del(&tmp_aeb->u.list);
+				kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 			}
 
 			new_aeb = kmem_cache_alloc(ai->aeb_slab_cache,
@@ -846,16 +846,16 @@
 	ret = UBI_BAD_FASTMAP;
 fail:
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &used, u.list) {
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 		list_del(&tmp_aeb->u.list);
+		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 	}
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &eba_orphans, u.list) {
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 		list_del(&tmp_aeb->u.list);
+		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 	}
 	list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &free, u.list) {
-		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 		list_del(&tmp_aeb->u.list);
+		kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
 	}
 
 	return ret;
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 6d20fbd..dcde5605 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -181,7 +181,7 @@
  */
 static inline void __disable_port(struct port *port)
 {
-	bond_set_slave_inactive_flags(port->slave);
+	bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER);
 }
 
 /**
@@ -193,7 +193,7 @@
 	struct slave *slave = port->slave;
 
 	if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev))
-		bond_set_slave_active_flags(slave);
+		bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER);
 }
 
 /**
@@ -2062,6 +2062,7 @@
 	struct list_head *iter;
 	struct slave *slave;
 	struct port *port;
+	bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
 
 	read_lock(&bond->lock);
 	rcu_read_lock();
@@ -2119,8 +2120,19 @@
 	}
 
 re_arm:
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		if (slave->should_notify) {
+			should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
+			break;
+		}
+	}
 	rcu_read_unlock();
 	read_unlock(&bond->lock);
+
+	if (should_notify_rtnl && rtnl_trylock()) {
+		bond_slave_state_notify(bond);
+		rtnl_unlock();
+	}
 	queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
 }
 
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index a2c4747..e8f133e 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -730,7 +730,7 @@
 			client_info->ntt = 0;
 		}
 
-		if (!vlan_get_tag(skb, &client_info->vlan_id))
+		if (vlan_get_tag(skb, &client_info->vlan_id))
 			client_info->vlan_id = 0;
 
 		if (!client_info->assigned) {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1c6104d..e5628fc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -829,21 +829,25 @@
 	if (bond_is_lb(bond)) {
 		bond_alb_handle_active_change(bond, new_active);
 		if (old_active)
-			bond_set_slave_inactive_flags(old_active);
+			bond_set_slave_inactive_flags(old_active,
+						      BOND_SLAVE_NOTIFY_NOW);
 		if (new_active)
-			bond_set_slave_active_flags(new_active);
+			bond_set_slave_active_flags(new_active,
+						    BOND_SLAVE_NOTIFY_NOW);
 	} else {
 		rcu_assign_pointer(bond->curr_active_slave, new_active);
 	}
 
 	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
 		if (old_active)
-			bond_set_slave_inactive_flags(old_active);
+			bond_set_slave_inactive_flags(old_active,
+						      BOND_SLAVE_NOTIFY_NOW);
 
 		if (new_active) {
 			bool should_notify_peers = false;
 
-			bond_set_slave_active_flags(new_active);
+			bond_set_slave_active_flags(new_active,
+						    BOND_SLAVE_NOTIFY_NOW);
 
 			if (bond->params.fail_over_mac)
 				bond_do_fail_over_mac(bond, new_active,
@@ -1193,6 +1197,11 @@
 		return -EBUSY;
 	}
 
+	if (bond_dev == slave_dev) {
+		pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name);
+		return -EPERM;
+	}
+
 	/* vlan challenged mutual exclusion */
 	/* no need to lock since we're protected by rtnl_lock */
 	if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
@@ -1463,14 +1472,15 @@
 
 	switch (bond->params.mode) {
 	case BOND_MODE_ACTIVEBACKUP:
-		bond_set_slave_inactive_flags(new_slave);
+		bond_set_slave_inactive_flags(new_slave,
+					      BOND_SLAVE_NOTIFY_NOW);
 		break;
 	case BOND_MODE_8023AD:
 		/* in 802.3ad mode, the internal mechanism
 		 * will activate the slaves in the selected
 		 * aggregator
 		 */
-		bond_set_slave_inactive_flags(new_slave);
+		bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
 		/* if this is the first slave */
 		if (!prev_slave) {
 			SLAVE_AD_INFO(new_slave).id = 1;
@@ -1488,7 +1498,7 @@
 	case BOND_MODE_TLB:
 	case BOND_MODE_ALB:
 		bond_set_active_slave(new_slave);
-		bond_set_slave_inactive_flags(new_slave);
+		bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
 		break;
 	default:
 		pr_debug("This slave is always active in trunk mode\n");
@@ -1654,9 +1664,6 @@
 		return -EINVAL;
 	}
 
-	/* release the slave from its bond */
-	bond->slave_cnt--;
-
 	bond_sysfs_slave_del(slave);
 
 	bond_upper_dev_unlink(bond_dev, slave_dev);
@@ -1738,6 +1745,7 @@
 
 	unblock_netpoll_tx();
 	synchronize_rcu();
+	bond->slave_cnt--;
 
 	if (!bond_has_slaves(bond)) {
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
@@ -2015,7 +2023,8 @@
 
 			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
 			    bond->params.mode == BOND_MODE_8023AD)
-				bond_set_slave_inactive_flags(slave);
+				bond_set_slave_inactive_flags(slave,
+							      BOND_SLAVE_NOTIFY_NOW);
 
 			pr_info("%s: link status definitely down for interface %s, disabling it\n",
 				bond->dev->name, slave->dev->name);
@@ -2562,7 +2571,8 @@
 				slave->link = BOND_LINK_UP;
 				if (bond->current_arp_slave) {
 					bond_set_slave_inactive_flags(
-						bond->current_arp_slave);
+						bond->current_arp_slave,
+						BOND_SLAVE_NOTIFY_NOW);
 					bond->current_arp_slave = NULL;
 				}
 
@@ -2582,7 +2592,8 @@
 				slave->link_failure_count++;
 
 			slave->link = BOND_LINK_DOWN;
-			bond_set_slave_inactive_flags(slave);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_NOW);
 
 			pr_info("%s: link status definitely down for interface %s, disabling it\n",
 				bond->dev->name, slave->dev->name);
@@ -2615,17 +2626,17 @@
 
 /*
  * Send ARP probes for active-backup mode ARP monitor.
+ *
+ * Called with rcu_read_lock hold.
  */
 static bool bond_ab_arp_probe(struct bonding *bond)
 {
 	struct slave *slave, *before = NULL, *new_slave = NULL,
-		     *curr_arp_slave, *curr_active_slave;
+		     *curr_arp_slave = rcu_dereference(bond->current_arp_slave),
+		     *curr_active_slave = rcu_dereference(bond->curr_active_slave);
 	struct list_head *iter;
 	bool found = false;
-
-	rcu_read_lock();
-	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
-	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
 
 	if (curr_arp_slave && curr_active_slave)
 		pr_info("PROBE: c_arp %s && cas %s BAD\n",
@@ -2634,32 +2645,23 @@
 
 	if (curr_active_slave) {
 		bond_arp_send_all(bond, curr_active_slave);
-		rcu_read_unlock();
-		return true;
+		return should_notify_rtnl;
 	}
-	rcu_read_unlock();
 
 	/* if we don't have a curr_active_slave, search for the next available
 	 * backup slave from the current_arp_slave and make it the candidate
 	 * for becoming the curr_active_slave
 	 */
 
-	if (!rtnl_trylock())
-		return false;
-	/* curr_arp_slave might have gone away */
-	curr_arp_slave = ACCESS_ONCE(bond->current_arp_slave);
-
 	if (!curr_arp_slave) {
-		curr_arp_slave = bond_first_slave(bond);
-		if (!curr_arp_slave) {
-			rtnl_unlock();
-			return true;
-		}
+		curr_arp_slave = bond_first_slave_rcu(bond);
+		if (!curr_arp_slave)
+			return should_notify_rtnl;
 	}
 
-	bond_set_slave_inactive_flags(curr_arp_slave);
+	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
 
-	bond_for_each_slave(bond, slave, iter) {
+	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (!found && !before && IS_UP(slave->dev))
 			before = slave;
 
@@ -2677,7 +2679,8 @@
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			bond_set_slave_inactive_flags(slave);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_LATER);
 
 			pr_info("%s: backup interface %s is now down.\n",
 				bond->dev->name, slave->dev->name);
@@ -2689,26 +2692,31 @@
 	if (!new_slave && before)
 		new_slave = before;
 
-	if (!new_slave) {
-		rtnl_unlock();
-		return true;
-	}
+	if (!new_slave)
+		goto check_state;
 
 	new_slave->link = BOND_LINK_BACK;
-	bond_set_slave_active_flags(new_slave);
+	bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
 	bond_arp_send_all(bond, new_slave);
 	new_slave->jiffies = jiffies;
 	rcu_assign_pointer(bond->current_arp_slave, new_slave);
-	rtnl_unlock();
 
-	return true;
+check_state:
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		if (slave->should_notify) {
+			should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
+			break;
+		}
+	}
+	return should_notify_rtnl;
 }
 
 static void bond_activebackup_arp_mon(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    arp_work.work);
-	bool should_notify_peers = false, should_commit = false;
+	bool should_notify_peers = false;
+	bool should_notify_rtnl = false;
 	int delta_in_ticks;
 
 	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
@@ -2717,11 +2725,12 @@
 		goto re_arm;
 
 	rcu_read_lock();
-	should_notify_peers = bond_should_notify_peers(bond);
-	should_commit = bond_ab_arp_inspect(bond);
-	rcu_read_unlock();
 
-	if (should_commit) {
+	should_notify_peers = bond_should_notify_peers(bond);
+
+	if (bond_ab_arp_inspect(bond)) {
+		rcu_read_unlock();
+
 		/* Race avoidance with bond_close flush of workqueue */
 		if (!rtnl_trylock()) {
 			delta_in_ticks = 1;
@@ -2730,23 +2739,28 @@
 		}
 
 		bond_ab_arp_commit(bond);
+
 		rtnl_unlock();
+		rcu_read_lock();
 	}
 
-	if (!bond_ab_arp_probe(bond)) {
-		/* rtnl locking failed, re-arm */
-		delta_in_ticks = 1;
-		should_notify_peers = false;
-	}
+	should_notify_rtnl = bond_ab_arp_probe(bond);
+	rcu_read_unlock();
 
 re_arm:
 	if (bond->params.arp_interval)
 		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
 
-	if (should_notify_peers) {
+	if (should_notify_peers || should_notify_rtnl) {
 		if (!rtnl_trylock())
 			return;
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+
+		if (should_notify_peers)
+			call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
+						 bond->dev);
+		if (should_notify_rtnl)
+			bond_slave_state_notify(bond);
+
 		rtnl_unlock();
 	}
 }
@@ -3046,9 +3060,11 @@
 		bond_for_each_slave(bond, slave, iter) {
 			if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
 				&& (slave != bond->curr_active_slave)) {
-				bond_set_slave_inactive_flags(slave);
+				bond_set_slave_inactive_flags(slave,
+							      BOND_SLAVE_NOTIFY_NOW);
 			} else {
-				bond_set_slave_active_flags(slave);
+				bond_set_slave_active_flags(slave,
+							    BOND_SLAVE_NOTIFY_NOW);
 			}
 		}
 		read_unlock(&bond->curr_slave_lock);
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index c378784..298c265 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -121,6 +121,7 @@
 static struct bond_opt_value bond_lp_interval_tbl[] = {
 	{ "minval",  1,       BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT},
 	{ "maxval",  INT_MAX, BOND_VALFLAG_MAX},
+	{ NULL,      -1,      0},
 };
 
 static struct bond_option bond_opts[] = {
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 86ccfb9..2b0fdec 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -195,7 +195,8 @@
 	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
-	       inactive:1; /* indicates inactive slave */
+	       inactive:1, /* indicates inactive slave */
+	       should_notify:1; /* indicateds whether the state changed */
 	u8     duplex;
 	u32    original_mtu;
 	u32    link_failure_count;
@@ -303,6 +304,24 @@
 	}
 }
 
+static inline void bond_set_slave_state(struct slave *slave,
+					int slave_state, bool notify)
+{
+	if (slave->backup == slave_state)
+		return;
+
+	slave->backup = slave_state;
+	if (notify) {
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL);
+		slave->should_notify = 0;
+	} else {
+		if (slave->should_notify)
+			slave->should_notify = 0;
+		else
+			slave->should_notify = 1;
+	}
+}
+
 static inline void bond_slave_state_change(struct bonding *bond)
 {
 	struct list_head *iter;
@@ -316,6 +335,19 @@
 	}
 }
 
+static inline void bond_slave_state_notify(struct bonding *bond)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter) {
+		if (tmp->should_notify) {
+			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_KERNEL);
+			tmp->should_notify = 0;
+		}
+	}
+}
+
 static inline int bond_slave_state(struct slave *slave)
 {
 	return slave->backup;
@@ -343,6 +375,9 @@
 #define BOND_ARP_VALIDATE_ALL		(BOND_ARP_VALIDATE_ACTIVE | \
 					 BOND_ARP_VALIDATE_BACKUP)
 
+#define BOND_SLAVE_NOTIFY_NOW		true
+#define BOND_SLAVE_NOTIFY_LATER		false
+
 static inline int slave_do_arp_validate(struct bonding *bond,
 					struct slave *slave)
 {
@@ -394,17 +429,19 @@
 }
 #endif
 
-static inline void bond_set_slave_inactive_flags(struct slave *slave)
+static inline void bond_set_slave_inactive_flags(struct slave *slave,
+						 bool notify)
 {
 	if (!bond_is_lb(slave->bond))
-		bond_set_backup_slave(slave);
+		bond_set_slave_state(slave, BOND_STATE_BACKUP, notify);
 	if (!slave->bond->params.all_slaves_active)
 		slave->inactive = 1;
 }
 
-static inline void bond_set_slave_active_flags(struct slave *slave)
+static inline void bond_set_slave_active_flags(struct slave *slave,
+					       bool notify)
 {
-	bond_set_active_slave(slave);
+	bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify);
 	slave->inactive = 0;
 }
 
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 320bef2..61376ab 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -144,6 +144,8 @@
 
 #define FLEXCAN_MB_CODE_MASK		(0xf0ffffff)
 
+#define FLEXCAN_TIMEOUT_US             (50)
+
 /*
  * FLEXCAN hardware feature flags
  *
@@ -262,6 +264,22 @@
 }
 #endif
 
+static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
+{
+	if (!priv->reg_xceiver)
+		return 0;
+
+	return regulator_enable(priv->reg_xceiver);
+}
+
+static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv)
+{
+	if (!priv->reg_xceiver)
+		return 0;
+
+	return regulator_disable(priv->reg_xceiver);
+}
+
 static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv,
 					      u32 reg_esr)
 {
@@ -269,26 +287,95 @@
 		(reg_esr & FLEXCAN_ESR_ERR_BUS);
 }
 
-static inline void flexcan_chip_enable(struct flexcan_priv *priv)
+static int flexcan_chip_enable(struct flexcan_priv *priv)
 {
 	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
 	u32 reg;
 
 	reg = flexcan_read(&regs->mcr);
 	reg &= ~FLEXCAN_MCR_MDIS;
 	flexcan_write(reg, &regs->mcr);
 
-	udelay(10);
+	while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK))
+		usleep_range(10, 20);
+
+	if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)
+		return -ETIMEDOUT;
+
+	return 0;
 }
 
-static inline void flexcan_chip_disable(struct flexcan_priv *priv)
+static int flexcan_chip_disable(struct flexcan_priv *priv)
 {
 	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
 	u32 reg;
 
 	reg = flexcan_read(&regs->mcr);
 	reg |= FLEXCAN_MCR_MDIS;
 	flexcan_write(reg, &regs->mcr);
+
+	while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK))
+		usleep_range(10, 20);
+
+	if (!(flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int flexcan_chip_freeze(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate;
+	u32 reg;
+
+	reg = flexcan_read(&regs->mcr);
+	reg |= FLEXCAN_MCR_HALT;
+	flexcan_write(reg, &regs->mcr);
+
+	while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
+		usleep_range(100, 200);
+
+	if (!(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int flexcan_chip_unfreeze(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
+	u32 reg;
+
+	reg = flexcan_read(&regs->mcr);
+	reg &= ~FLEXCAN_MCR_HALT;
+	flexcan_write(reg, &regs->mcr);
+
+	while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK))
+		usleep_range(10, 20);
+
+	if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int flexcan_chip_softreset(struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->base;
+	unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
+
+	flexcan_write(FLEXCAN_MCR_SOFTRST, &regs->mcr);
+	while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_SOFTRST))
+		usleep_range(10, 20);
+
+	if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_SOFTRST)
+		return -ETIMEDOUT;
+
+	return 0;
 }
 
 static int flexcan_get_berr_counter(const struct net_device *dev,
@@ -709,19 +796,14 @@
 	u32 reg_mcr, reg_ctrl;
 
 	/* enable module */
-	flexcan_chip_enable(priv);
+	err = flexcan_chip_enable(priv);
+	if (err)
+		return err;
 
 	/* soft reset */
-	flexcan_write(FLEXCAN_MCR_SOFTRST, &regs->mcr);
-	udelay(10);
-
-	reg_mcr = flexcan_read(&regs->mcr);
-	if (reg_mcr & FLEXCAN_MCR_SOFTRST) {
-		netdev_err(dev, "Failed to softreset can module (mcr=0x%08x)\n",
-			   reg_mcr);
-		err = -ENODEV;
-		goto out;
-	}
+	err = flexcan_chip_softreset(priv);
+	if (err)
+		goto out_chip_disable;
 
 	flexcan_set_bittiming(dev);
 
@@ -788,16 +870,14 @@
 	if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES)
 		flexcan_write(0x0, &regs->rxfgmask);
 
-	if (priv->reg_xceiver)	{
-		err = regulator_enable(priv->reg_xceiver);
-		if (err)
-			goto out;
-	}
+	err = flexcan_transceiver_enable(priv);
+	if (err)
+		goto out_chip_disable;
 
 	/* synchronize with the can bus */
-	reg_mcr = flexcan_read(&regs->mcr);
-	reg_mcr &= ~FLEXCAN_MCR_HALT;
-	flexcan_write(reg_mcr, &regs->mcr);
+	err = flexcan_chip_unfreeze(priv);
+	if (err)
+		goto out_transceiver_disable;
 
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
@@ -810,7 +890,9 @@
 
 	return 0;
 
- out:
+ out_transceiver_disable:
+	flexcan_transceiver_disable(priv);
+ out_chip_disable:
 	flexcan_chip_disable(priv);
 	return err;
 }
@@ -825,18 +907,17 @@
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct flexcan_regs __iomem *regs = priv->base;
-	u32 reg;
+
+	/* freeze + disable module */
+	flexcan_chip_freeze(priv);
+	flexcan_chip_disable(priv);
 
 	/* Disable all interrupts */
 	flexcan_write(0, &regs->imask1);
+	flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
+		      &regs->ctrl);
 
-	/* Disable + halt module */
-	reg = flexcan_read(&regs->mcr);
-	reg |= FLEXCAN_MCR_MDIS | FLEXCAN_MCR_HALT;
-	flexcan_write(reg, &regs->mcr);
-
-	if (priv->reg_xceiver)
-		regulator_disable(priv->reg_xceiver);
+	flexcan_transceiver_disable(priv);
 	priv->can.state = CAN_STATE_STOPPED;
 
 	return;
@@ -866,7 +947,7 @@
 	/* start chip and queuing */
 	err = flexcan_chip_start(dev);
 	if (err)
-		goto out_close;
+		goto out_free_irq;
 
 	can_led_event(dev, CAN_LED_EVENT_OPEN);
 
@@ -875,6 +956,8 @@
 
 	return 0;
 
+ out_free_irq:
+	free_irq(dev->irq, dev);
  out_close:
 	close_candev(dev);
  out_disable_per:
@@ -945,12 +1028,16 @@
 		goto out_disable_ipg;
 
 	/* select "bus clock", chip must be disabled */
-	flexcan_chip_disable(priv);
+	err = flexcan_chip_disable(priv);
+	if (err)
+		goto out_disable_per;
 	reg = flexcan_read(&regs->ctrl);
 	reg |= FLEXCAN_CTRL_CLK_SRC;
 	flexcan_write(reg, &regs->ctrl);
 
-	flexcan_chip_enable(priv);
+	err = flexcan_chip_enable(priv);
+	if (err)
+		goto out_chip_disable;
 
 	/* set freeze, halt and activate FIFO, restrict register access */
 	reg = flexcan_read(&regs->mcr);
@@ -967,14 +1054,15 @@
 	if (!(reg & FLEXCAN_MCR_FEN)) {
 		netdev_err(dev, "Could not enable RX FIFO, unsupported core\n");
 		err = -ENODEV;
-		goto out_disable_per;
+		goto out_chip_disable;
 	}
 
 	err = register_candev(dev);
 
- out_disable_per:
 	/* disable core and turn off clocks */
+ out_chip_disable:
 	flexcan_chip_disable(priv);
+ out_disable_per:
 	clk_disable_unprepare(priv->clk_per);
  out_disable_ipg:
 	clk_disable_unprepare(priv->clk_ipg);
@@ -1104,9 +1192,10 @@
 static int flexcan_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
+	struct flexcan_priv *priv = netdev_priv(dev);
 
 	unregister_flexcandev(dev);
-
+	netif_napi_del(&priv->napi);
 	free_candev(dev);
 
 	return 0;
@@ -1117,8 +1206,11 @@
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
+	int err;
 
-	flexcan_chip_disable(priv);
+	err = flexcan_chip_disable(priv);
+	if (err)
+		return err;
 
 	if (netif_running(dev)) {
 		netif_stop_queue(dev);
@@ -1139,9 +1231,7 @@
 		netif_device_attach(dev);
 		netif_start_queue(dev);
 	}
-	flexcan_chip_enable(priv);
-
-	return 0;
+	return flexcan_chip_enable(priv);
 }
 #endif /* CONFIG_PM_SLEEP */
 
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 1f7b5aa..8a7bf7d 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1484,6 +1484,10 @@
 	add_timer(&bp->timer);
 
 	b44_enable_ints(bp);
+
+	if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+		phy_start(bp->phydev);
+
 	netif_start_queue(dev);
 out:
 	return err;
@@ -1646,6 +1650,9 @@
 
 	netif_stop_queue(dev);
 
+	if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+		phy_stop(bp->phydev);
+
 	napi_disable(&bp->napi);
 
 	del_timer_sync(&bp->timer);
@@ -2222,7 +2229,12 @@
 	}
 
 	if (status_changed) {
-		b44_check_phy(bp);
+		u32 val = br32(bp, B44_TX_CTRL);
+		if (bp->flags & B44_FLAG_FULL_DUPLEX)
+			val |= TX_CTRL_DUPLEX;
+		else
+			val &= ~TX_CTRL_DUPLEX;
+		bw32(bp, B44_TX_CTRL, val);
 		phy_print_status(phydev);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index cda25ac..6c9e1c9 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -2507,6 +2507,7 @@
 
 	bp->fw_wr_seq++;
 	msg_data |= bp->fw_wr_seq;
+	bp->fw_last_msg = msg_data;
 
 	bnx2_shmem_wr(bp, BNX2_DRV_MB, msg_data);
 
@@ -4000,8 +4001,23 @@
 			wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL;
 	}
 
-	if (!(bp->flags & BNX2_FLAG_NO_WOL))
-		bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT3 | wol_msg, 1, 0);
+	if (!(bp->flags & BNX2_FLAG_NO_WOL)) {
+		u32 val;
+
+		wol_msg |= BNX2_DRV_MSG_DATA_WAIT3;
+		if (bp->fw_last_msg || BNX2_CHIP(bp) != BNX2_CHIP_5709) {
+			bnx2_fw_sync(bp, wol_msg, 1, 0);
+			return;
+		}
+		/* Tell firmware not to power down the PHY yet, otherwise
+		 * the chip will take a long time to respond to MMIO reads.
+		 */
+		val = bnx2_shmem_rd(bp, BNX2_PORT_FEATURE);
+		bnx2_shmem_wr(bp, BNX2_PORT_FEATURE,
+			      val | BNX2_PORT_FEATURE_ASF_ENABLED);
+		bnx2_fw_sync(bp, wol_msg, 1, 0);
+		bnx2_shmem_wr(bp, BNX2_PORT_FEATURE, val);
+	}
 
 }
 
@@ -4033,9 +4049,22 @@
 
 			if (bp->wol)
 				pci_set_power_state(bp->pdev, PCI_D3hot);
-		} else {
-			pci_set_power_state(bp->pdev, PCI_D3hot);
+			break;
+
 		}
+		if (!bp->fw_last_msg && BNX2_CHIP(bp) == BNX2_CHIP_5709) {
+			u32 val;
+
+			/* Tell firmware not to power down the PHY yet,
+			 * otherwise the other port may not respond to
+			 * MMIO reads.
+			 */
+			val = bnx2_shmem_rd(bp, BNX2_BC_STATE_CONDITION);
+			val &= ~BNX2_CONDITION_PM_STATE_MASK;
+			val |= BNX2_CONDITION_PM_STATE_UNPREP;
+			bnx2_shmem_wr(bp, BNX2_BC_STATE_CONDITION, val);
+		}
+		pci_set_power_state(bp->pdev, PCI_D3hot);
 
 		/* No more memory access after this point until
 		 * device is brought back to D0.
diff --git a/drivers/net/ethernet/broadcom/bnx2.h b/drivers/net/ethernet/broadcom/bnx2.h
index f1cf2c4..e341bc3 100644
--- a/drivers/net/ethernet/broadcom/bnx2.h
+++ b/drivers/net/ethernet/broadcom/bnx2.h
@@ -6900,6 +6900,7 @@
 
 	u16			fw_wr_seq;
 	u16			fw_drv_pulse_wr_seq;
+	u32			fw_last_msg;
 
 	int			rx_max_ring;
 	int			rx_ring_size;
@@ -7406,6 +7407,10 @@
 #define BNX2_CONDITION_MFW_RUN_NCSI		 0x00006000
 #define BNX2_CONDITION_MFW_RUN_NONE		 0x0000e000
 #define BNX2_CONDITION_MFW_RUN_MASK		 0x0000e000
+#define BNX2_CONDITION_PM_STATE_MASK		 0x00030000
+#define BNX2_CONDITION_PM_STATE_FULL		 0x00030000
+#define BNX2_CONDITION_PM_STATE_PREP		 0x00020000
+#define BNX2_CONDITION_PM_STATE_UNPREP		 0x00010000
 
 #define BNX2_BC_STATE_DEBUG_CMD			0x1dc
 #define BNX2_BC_STATE_BC_DBG_CMD_SIGNATURE	 0x42440000
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 66c0df7..dbcff50 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3875,7 +3875,9 @@
 						     xmit_type);
 		}
 
-		/* Add the macs to the parsing BD this is a vf */
+		/* Add the macs to the parsing BD if this is a vf or if
+		 * Tx Switching is enabled.
+		 */
 		if (IS_VF(bp)) {
 			/* override GRE parameters in BD */
 			bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi,
@@ -3887,6 +3889,11 @@
 					      &pbd_e2->data.mac_addr.dst_mid,
 					      &pbd_e2->data.mac_addr.dst_lo,
 					      eth->h_dest);
+		} else if (bp->flags & TX_SWITCHING) {
+			bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi,
+					      &pbd_e2->data.mac_addr.dst_mid,
+					      &pbd_e2->data.mac_addr.dst_lo,
+					      eth->h_dest);
 		}
 
 		SET_FLAG(pbd_e2_parsing_data,
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3167ed6..3b6d0ba 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6843,8 +6843,7 @@
 
 		work_mask |= opaque_key;
 
-		if ((desc->err_vlan & RXD_ERR_MASK) != 0 &&
-		    (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) {
+		if (desc->err_vlan & RXD_ERR_MASK) {
 		drop_it:
 			tg3_recycle_rx(tnapi, tpr, opaque_key,
 				       desc_idx, *post_ptr);
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ef47238..04321e5 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2608,7 +2608,11 @@
 #define RXD_ERR_TOO_SMALL		0x00400000
 #define RXD_ERR_NO_RESOURCES		0x00800000
 #define RXD_ERR_HUGE_FRAME		0x01000000
-#define RXD_ERR_MASK			0xffff0000
+
+#define RXD_ERR_MASK	(RXD_ERR_BAD_CRC | RXD_ERR_COLLISION |		\
+			 RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE |	\
+			 RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL |		\
+			 RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME)
 
 	u32				reserved;
 	u32				opaque;
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 1803c39..354ae97 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1704,7 +1704,7 @@
 	while (!bfa_raw_sem_get(bar)) {
 		if (--n <= 0)
 			return BFA_STATUS_BADFLASH;
-		udelay(10000);
+		mdelay(10);
 	}
 	return BFA_STATUS_OK;
 }
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index cf64f3d..4ad1187 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -707,7 +707,8 @@
 		else
 			skb_checksum_none_assert(skb);
 
-		if (flags & BNA_CQ_EF_VLAN)
+		if ((flags & BNA_CQ_EF_VLAN) &&
+		    (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(cmpl->vlan_tag));
 
 		if (BNAD_RXBUF_IS_SK_BUFF(unmap_q->type))
@@ -2094,7 +2095,9 @@
 		rx_config->q1_buf_size = BFI_SMALL_RXBUF_SIZE;
 	}
 
-	rx_config->vlan_strip_status = BNA_STATUS_T_ENABLED;
+	rx_config->vlan_strip_status =
+		(bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) ?
+		BNA_STATUS_T_ENABLED : BNA_STATUS_T_DISABLED;
 }
 
 static void
@@ -3245,11 +3248,6 @@
 			BNA_RXMODE_ALLMULTI;
 	bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask, NULL);
 
-	if (bnad->cfg_flags & BNAD_CF_PROMISC)
-		bna_rx_vlan_strip_disable(bnad->rx_info[0].rx);
-	else
-		bna_rx_vlan_strip_enable(bnad->rx_info[0].rx);
-
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
 
@@ -3374,6 +3372,27 @@
 	return 0;
 }
 
+static int bnad_set_features(struct net_device *dev, netdev_features_t features)
+{
+	struct bnad *bnad = netdev_priv(dev);
+	netdev_features_t changed = features ^ dev->features;
+
+	if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(dev)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&bnad->bna_lock, flags);
+
+		if (features & NETIF_F_HW_VLAN_CTAG_RX)
+			bna_rx_vlan_strip_enable(bnad->rx_info[0].rx);
+		else
+			bna_rx_vlan_strip_disable(bnad->rx_info[0].rx);
+
+		spin_unlock_irqrestore(&bnad->bna_lock, flags);
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void
 bnad_netpoll(struct net_device *netdev)
@@ -3421,6 +3440,7 @@
 	.ndo_change_mtu		= bnad_change_mtu,
 	.ndo_vlan_rx_add_vid    = bnad_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = bnad_vlan_rx_kill_vid,
+	.ndo_set_features	= bnad_set_features,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller    = bnad_netpoll
 #endif
@@ -3433,14 +3453,14 @@
 
 	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX;
+		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX |
+		NETIF_F_HW_VLAN_CTAG_RX;
 
 	netdev->vlan_features = NETIF_F_SG | NETIF_F_HIGHDMA |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		NETIF_F_TSO | NETIF_F_TSO6;
 
-	netdev->features |= netdev->hw_features |
-		NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER;
+	netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	if (using_dac)
 		netdev->features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 3190d38..d0c38e0 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -632,11 +632,16 @@
 					   "Unable to allocate sk_buff\n");
 				break;
 			}
-			bp->rx_skbuff[entry] = skb;
 
 			/* now fill corresponding descriptor entry */
 			paddr = dma_map_single(&bp->pdev->dev, skb->data,
 					       bp->rx_buffer_size, DMA_FROM_DEVICE);
+			if (dma_mapping_error(&bp->pdev->dev, paddr)) {
+				dev_kfree_skb(skb);
+				break;
+			}
+
+			bp->rx_skbuff[entry] = skb;
 
 			if (entry == RX_RING_SIZE - 1)
 				paddr |= MACB_BIT(RX_WRAP);
@@ -725,7 +730,7 @@
 		skb_put(skb, len);
 		addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, addr));
 		dma_unmap_single(&bp->pdev->dev, addr,
-				 len, DMA_FROM_DEVICE);
+				 bp->rx_buffer_size, DMA_FROM_DEVICE);
 
 		skb->protocol = eth_type_trans(skb, bp->dev);
 		skb_checksum_none_assert(skb);
@@ -1036,11 +1041,15 @@
 	}
 
 	entry = macb_tx_ring_wrap(bp->tx_head);
-	bp->tx_head++;
 	netdev_vdbg(bp->dev, "Allocated ring entry %u\n", entry);
 	mapping = dma_map_single(&bp->pdev->dev, skb->data,
 				 len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&bp->pdev->dev, mapping)) {
+		kfree_skb(skb);
+		goto unlock;
+	}
 
+	bp->tx_head++;
 	tx_skb = &bp->tx_skb[entry];
 	tx_skb->skb = skb;
 	tx_skb->mapping = mapping;
@@ -1066,6 +1075,7 @@
 	if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1)
 		netif_stop_queue(dev);
 
+unlock:
 	spin_unlock_irqrestore(&bp->lock, flags);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 43ab35f..34e2488 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -6179,6 +6179,7 @@
 	.id_table = cxgb4_pci_tbl,
 	.probe    = init_one,
 	.remove   = remove_one,
+	.shutdown = remove_one,
 	.err_handler = &cxgb4_eeh,
 };
 
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 8d09615..05529e2 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -350,11 +350,13 @@
 	u32 roce_drops_crc;
 };
 
+/* A vlan-id of 0xFFFF must be used to clear transparent vlan-tagging */
+#define BE_RESET_VLAN_TAG_ID	0xFFFF
+
 struct be_vf_cfg {
 	unsigned char mac_addr[ETH_ALEN];
 	int if_handle;
 	int pmac_id;
-	u16 def_vid;
 	u16 vlan_tag;
 	u32 tx_rate;
 };
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 04ac9c6..36c8061 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -913,24 +913,14 @@
 	return BE3_chip(adapter) && be_ipv6_exthdr_check(skb);
 }
 
-static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
-					   struct sk_buff *skb,
-					   bool *skip_hw_vlan)
+static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
+						  struct sk_buff *skb,
+						  bool *skip_hw_vlan)
 {
 	struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 	unsigned int eth_hdr_len;
 	struct iphdr *ip;
 
-	/* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or less
-	 * may cause a transmit stall on that port. So the work-around is to
-	 * pad short packets (<= 32 bytes) to a 36-byte length.
-	 */
-	if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) {
-		if (skb_padto(skb, 36))
-			goto tx_drop;
-		skb->len = 36;
-	}
-
 	/* For padded packets, BE HW modifies tot_len field in IP header
 	 * incorrecly when VLAN tag is inserted by HW.
 	 * For padded packets, Lancer computes incorrect checksum.
@@ -959,7 +949,7 @@
 	    vlan_tx_tag_present(skb)) {
 		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
 		if (unlikely(!skb))
-			goto tx_drop;
+			goto err;
 	}
 
 	/* HW may lockup when VLAN HW tagging is requested on
@@ -981,15 +971,39 @@
 	    be_vlan_tag_tx_chk(adapter, skb)) {
 		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
 		if (unlikely(!skb))
-			goto tx_drop;
+			goto err;
 	}
 
 	return skb;
 tx_drop:
 	dev_kfree_skb_any(skb);
+err:
 	return NULL;
 }
 
+static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
+					   struct sk_buff *skb,
+					   bool *skip_hw_vlan)
+{
+	/* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or
+	 * less may cause a transmit stall on that port. So the work-around is
+	 * to pad short packets (<= 32 bytes) to a 36-byte length.
+	 */
+	if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) {
+		if (skb_padto(skb, 36))
+			return NULL;
+		skb->len = 36;
+	}
+
+	if (BEx_chip(adapter) || lancer_chip(adapter)) {
+		skb = be_lancer_xmit_workarounds(adapter, skb, skip_hw_vlan);
+		if (!skb)
+			return NULL;
+	}
+
+	return skb;
+}
+
 static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -1157,6 +1171,14 @@
 	return status;
 }
 
+static void be_clear_promisc(struct be_adapter *adapter)
+{
+	adapter->promiscuous = false;
+	adapter->flags &= ~BE_FLAGS_VLAN_PROMISC;
+
+	be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
+}
+
 static void be_set_rx_mode(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -1170,9 +1192,7 @@
 
 	/* BE was previously in promiscuous mode; disable it */
 	if (adapter->promiscuous) {
-		adapter->promiscuous = false;
-		be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
-
+		be_clear_promisc(adapter);
 		if (adapter->vlans_added)
 			be_vid_config(adapter);
 	}
@@ -1287,24 +1307,20 @@
 
 	if (vlan || qos) {
 		vlan |= qos << VLAN_PRIO_SHIFT;
-		if (vf_cfg->vlan_tag != vlan) {
-			/* If this is new value, program it. Else skip. */
-			vf_cfg->vlan_tag = vlan;
+		if (vf_cfg->vlan_tag != vlan)
 			status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
 						       vf_cfg->if_handle, 0);
-		}
 	} else {
 		/* Reset Transparent Vlan Tagging. */
-		vf_cfg->vlan_tag = 0;
-		vlan = vf_cfg->def_vid;
-		status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
-					       vf_cfg->if_handle, 0);
+		status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID,
+					       vf + 1, vf_cfg->if_handle, 0);
 	}
 
-
-	if (status)
+	if (!status)
+		vf_cfg->vlan_tag = vlan;
+	else
 		dev_info(&adapter->pdev->dev,
-				"VLAN %d config on VF %d failed\n", vlan, vf);
+			 "VLAN %d config on VF %d failed\n", vlan, vf);
 	return status;
 }
 
@@ -3013,11 +3029,11 @@
 
 static int be_vf_setup(struct be_adapter *adapter)
 {
-	struct be_vf_cfg *vf_cfg;
-	u16 def_vlan, lnk_speed;
-	int status, old_vfs, vf;
 	struct device *dev = &adapter->pdev->dev;
+	struct be_vf_cfg *vf_cfg;
+	int status, old_vfs, vf;
 	u32 privileges;
+	u16 lnk_speed;
 
 	old_vfs = pci_num_vf(adapter->pdev);
 	if (old_vfs) {
@@ -3084,12 +3100,6 @@
 		if (!status)
 			vf_cfg->tx_rate = lnk_speed;
 
-		status = be_cmd_get_hsw_config(adapter, &def_vlan,
-					       vf + 1, vf_cfg->if_handle, NULL);
-		if (status)
-			goto err;
-		vf_cfg->def_vid = def_vlan;
-
 		if (!old_vfs)
 			be_cmd_enable_vf(adapter, vf + 1);
 	}
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 903362a..03a3513 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -389,12 +389,6 @@
 			netdev_err(ndev, "Tx DMA memory map failed\n");
 		return NETDEV_TX_OK;
 	}
-	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
-	 * it's the last BD of the frame, and to put the CRC on the end.
-	 */
-	status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
-			| BD_ENET_TX_LAST | BD_ENET_TX_TC);
-	bdp->cbd_sc = status;
 
 	if (fep->bufdesc_ex) {
 
@@ -416,6 +410,13 @@
 		}
 	}
 
+	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
+	 * it's the last BD of the frame, and to put the CRC on the end.
+	 */
+	status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
+			| BD_ENET_TX_LAST | BD_ENET_TX_TC);
+	bdp->cbd_sc = status;
+
 	bdp_pre = fec_enet_get_prevdesc(bdp, fep);
 	if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
 	    !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
@@ -527,13 +528,6 @@
 	/* Clear any outstanding interrupt. */
 	writel(0xffc00000, fep->hwp + FEC_IEVENT);
 
-	/* Setup multicast filter. */
-	set_multicast_list(ndev);
-#ifndef CONFIG_M5272
-	writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
-	writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
-#endif
-
 	/* Set maximum receive buffer size. */
 	writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE);
 
@@ -654,6 +648,13 @@
 
 	writel(rcntl, fep->hwp + FEC_R_CNTRL);
 
+	/* Setup multicast filter. */
+	set_multicast_list(ndev);
+#ifndef CONFIG_M5272
+	writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
+	writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
+#endif
+
 	if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) {
 		/* enable ENET endian swap */
 		ecntl |= (1 << 8);
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 4be9715..1fc8334 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -522,10 +522,21 @@
 	return rc;
 }
 
+static u64 ibmveth_encode_mac_addr(u8 *mac)
+{
+	int i;
+	u64 encoded = 0;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		encoded = (encoded << 8) | mac[i];
+
+	return encoded;
+}
+
 static int ibmveth_open(struct net_device *netdev)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
-	u64 mac_address = 0;
+	u64 mac_address;
 	int rxq_entries = 1;
 	unsigned long lpar_rc;
 	int rc;
@@ -579,8 +590,7 @@
 	adapter->rx_queue.num_slots = rxq_entries;
 	adapter->rx_queue.toggle = 1;
 
-	memcpy(&mac_address, netdev->dev_addr, netdev->addr_len);
-	mac_address = mac_address >> 16;
+	mac_address = ibmveth_encode_mac_addr(netdev->dev_addr);
 
 	rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
 					adapter->rx_queue.queue_len;
@@ -1183,8 +1193,8 @@
 		/* add the addresses to the filter table */
 		netdev_for_each_mc_addr(ha, netdev) {
 			/* add the multicast address to the filter table */
-			unsigned long mcast_addr = 0;
-			memcpy(((char *)&mcast_addr)+2, ha->addr, ETH_ALEN);
+			u64 mcast_addr;
+			mcast_addr = ibmveth_encode_mac_addr(ha->addr);
 			lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
 						   IbmVethMcastAddFilter,
 						   mcast_addr);
@@ -1372,9 +1382,6 @@
 
 	netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
 
-	adapter->mac_addr = 0;
-	memcpy(&adapter->mac_addr, mac_addr_p, ETH_ALEN);
-
 	netdev->irq = dev->irq;
 	netdev->netdev_ops = &ibmveth_netdev_ops;
 	netdev->ethtool_ops = &netdev_ethtool_ops;
@@ -1383,7 +1390,7 @@
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	netdev->features |= netdev->hw_features;
 
-	memcpy(netdev->dev_addr, &adapter->mac_addr, netdev->addr_len);
+	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
 		struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 451ba79..1f37499 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -138,7 +138,6 @@
     struct napi_struct napi;
     struct net_device_stats stats;
     unsigned int mcastFilterSize;
-    unsigned long mac_addr;
     void * buffer_list_addr;
     void * filter_list_addr;
     dma_addr_t buffer_list_dma;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fad4531..84a96f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -742,6 +742,14 @@
 				err = mlx4_en_uc_steer_add(priv, new_mac,
 							   &qpn,
 							   &entry->reg_id);
+				if (err)
+					return err;
+				if (priv->tunnel_reg_id) {
+					mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+					priv->tunnel_reg_id = 0;
+				}
+				err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn,
+							       &priv->tunnel_reg_id);
 				return err;
 			}
 		}
@@ -1792,6 +1800,8 @@
 		mc_list[5] = priv->port;
 		mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
 				      mc_list, MLX4_PROT_ETH, mclist->reg_id);
+		if (mclist->tunnel_reg_id)
+			mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id);
 	}
 	mlx4_en_clear_list(dev);
 	list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 91b69ff..7e2995e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -129,13 +129,14 @@
 		[0] = "RSS support",
 		[1] = "RSS Toeplitz Hash Function support",
 		[2] = "RSS XOR Hash Function support",
-		[3] = "Device manage flow steering support",
+		[3] = "Device managed flow steering support",
 		[4] = "Automatic MAC reassignment support",
 		[5] = "Time stamping support",
 		[6] = "VST (control vlan insertion/stripping) support",
 		[7] = "FSM (MAC anti-spoofing) support",
 		[8] = "Dynamic QP updates support",
-		[9] = "TCP/IP offloads/flow-steering for VXLAN support"
+		[9] = "Device managed flow steering IPoIB support",
+		[10] = "TCP/IP offloads/flow-steering for VXLAN support"
 	};
 	int i;
 
@@ -859,7 +860,7 @@
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
 
 	/* For guests, disable vxlan tunneling */
-	MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_VXLAN);
 	field &= 0xf7;
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN);
 
@@ -869,7 +870,7 @@
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
 
 	/* For guests, disable mw type 2 */
-	MLX4_GET(bmme_flags, outbox, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+	MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 	bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN;
 	MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 
@@ -883,7 +884,7 @@
 	}
 
 	/* turn off ipoib managed steering for guests */
-	MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
 	field &= ~0x80;
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index d711158..936c153 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -150,6 +150,8 @@
 	struct pci_dev *pdev;
 };
 
+static atomic_t pf_loading = ATOMIC_INIT(0);
+
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -749,7 +751,7 @@
 			has_eth_port = true;
 	}
 
-	if (has_ib_port)
+	if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
 		request_module_nowait(IB_DRV_NAME);
 	if (has_eth_port)
 		request_module_nowait(EN_DRV_NAME);
@@ -1407,6 +1409,11 @@
 	u32 slave_read;
 	u32 cmd_channel_ver;
 
+	if (atomic_read(&pf_loading)) {
+		mlx4_warn(dev, "PF is not ready. Deferring probe\n");
+		return -EPROBE_DEFER;
+	}
+
 	mutex_lock(&priv->cmd.slave_cmd_mutex);
 	priv->cmd.max_cmds = 1;
 	mlx4_warn(dev, "Sending reset\n");
@@ -2319,7 +2326,11 @@
 
 		if (num_vfs) {
 			mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs);
+
+			atomic_inc(&pf_loading);
 			err = pci_enable_sriov(pdev, num_vfs);
+			atomic_dec(&pf_loading);
+
 			if (err) {
 				mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
 					 err);
@@ -2684,6 +2695,7 @@
 	.name		= DRV_NAME,
 	.id_table	= mlx4_pci_table,
 	.probe		= mlx4_init_one,
+	.shutdown	= mlx4_remove_one,
 	.remove		= mlx4_remove_one,
 	.err_handler    = &mlx4_err_handler,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6b65f77..7aec6c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -51,8 +51,8 @@
 
 #define DRV_NAME	"mlx4_core"
 #define PFX		DRV_NAME ": "
-#define DRV_VERSION	"1.1"
-#define DRV_RELDATE	"Dec, 2011"
+#define DRV_VERSION	"2.2-1"
+#define DRV_RELDATE	"Feb, 2014"
 
 #define MLX4_FS_UDP_UC_EN		(1 << 1)
 #define MLX4_FS_TCP_UC_EN		(1 << 2)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 9ca223b..b57e8c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -57,8 +57,8 @@
 #include "en_port.h"
 
 #define DRV_NAME	"mlx4_en"
-#define DRV_VERSION	"2.0"
-#define DRV_RELDATE	"Dec 2011"
+#define DRV_VERSION	"2.2-1"
+#define DRV_RELDATE	"Feb 2014"
 
 #define MLX4_EN_MSG_LEVEL	(NETIF_MSG_LINK | NETIF_MSG_IFDOWN)
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a064f06..23b7e2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -46,8 +46,8 @@
 #include "mlx5_core.h"
 
 #define DRIVER_NAME "mlx5_core"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE	"June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE	"Feb 2014"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox ConnectX-IB HCA core library");
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 4146664..27c4f13 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -340,6 +340,7 @@
 			if (qlcnic_sriov_vf_check(adapter))
 				return -EINVAL;
 			num_msix = 1;
+			adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
 			adapter->drv_tx_rings = QLCNIC_SINGLE_RING;
 		}
 	}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
index 77f1bce..7d4f549 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
@@ -807,7 +807,7 @@
 	    !type->tc_param_valid)
 		return;
 
-	if (tc < 0 || (tc > QLC_DCB_MAX_TC))
+	if (tc < 0 || (tc >= QLC_DCB_MAX_TC))
 		return;
 
 	tc_cfg = &type->tc_cfg[tc];
@@ -843,7 +843,7 @@
 	    !type->tc_param_valid)
 		return;
 
-	if (pgid < 0 || pgid > QLC_DCB_MAX_PG)
+	if (pgid < 0 || pgid >= QLC_DCB_MAX_PG)
 		return;
 
 	pgcfg = &type->pg_cfg[pgid];
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index ba78c74..1222865 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -816,9 +816,10 @@
 
 		if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
 			qlcnic_disable_multi_tx(adapter);
+			adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
 
 			err = qlcnic_enable_msi_legacy(adapter);
-			if (!err)
+			if (err)
 				return err;
 		}
 	}
@@ -3863,7 +3864,7 @@
 		strcpy(buf, "Tx");
 	}
 
-	if (!qlcnic_use_msi_x && !qlcnic_use_msi) {
+	if (!QLCNIC_IS_MSI_FAMILY(adapter)) {
 		netdev_err(netdev, "No RSS/TSS support in INT-x mode\n");
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 09acf15..e5277a6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -13,8 +13,6 @@
 #define QLC_VF_MIN_TX_RATE	100
 #define QLC_VF_MAX_TX_RATE	9999
 #define QLC_MAC_OPCODE_MASK	0x7
-#define QLC_MAC_STAR_ADD	6
-#define QLC_MAC_STAR_DEL	7
 #define QLC_VF_FLOOD_BIT	BIT_16
 #define QLC_FLOOD_MODE		0x5
 
@@ -1206,13 +1204,6 @@
 	struct qlcnic_vport *vp = vf->vp;
 	u8 op, new_op;
 
-	if (((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_ADD) ||
-	    ((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_DEL)) {
-		netdev_err(adapter->netdev, "MAC + any VLAN filter not allowed from VF %d\n",
-			   vf->pci_func);
-		return -EINVAL;
-	}
-
 	if (!(cmd->req.arg[1] & BIT_8))
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 91a67ae..3ff7bc3 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -209,7 +209,7 @@
 	[RTL_GIGA_MAC_VER_16] =
 		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K, true),
 	[RTL_GIGA_MAC_VER_17] =
-		_R("RTL8168b/8111b",	RTL_TD_1, NULL, JUMBO_4K, false),
+		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K, false),
 	[RTL_GIGA_MAC_VER_18] =
 		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K, false),
 	[RTL_GIGA_MAC_VER_19] =
@@ -7118,6 +7118,8 @@
 	}
 
 	mutex_init(&tp->wk.mutex);
+	u64_stats_init(&tp->rx_stats.syncp);
+	u64_stats_init(&tp->tx_stats.syncp);
 
 	/* Get MAC address */
 	for (i = 0; i < ETH_ALEN; i++)
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index eb75fbd..d7a3682 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1668,6 +1668,13 @@
 	struct efx_ptp_data *ptp = efx->ptp_data;
 	int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
 
+	if (!ptp) {
+		if (net_ratelimit())
+			netif_warn(efx, drv, efx->net_dev,
+				   "Received PTP event but PTP not set up\n");
+		return;
+	}
+
 	if (!ptp->enabled)
 		return;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index 72d282b..c553f6b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -151,7 +151,7 @@
 					  sizeof(struct dma_desc)));
 }
 
-const struct stmmac_chain_mode_ops chain_mode_ops = {
+const struct stmmac_mode_ops chain_mode_ops = {
 	.init = stmmac_init_dma_chain,
 	.is_jumbo_frm = stmmac_is_jumbo_frm,
 	.jumbo_frm = stmmac_jumbo_frm,
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 7834a39..74610f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -419,20 +419,13 @@
 	unsigned int data;	/* MII Data */
 };
 
-struct stmmac_ring_mode_ops {
-	unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
-	unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum);
-	void (*refill_desc3) (void *priv, struct dma_desc *p);
-	void (*init_desc3) (struct dma_desc *p);
-	void (*clean_desc3) (void *priv, struct dma_desc *p);
-	int (*set_16kib_bfsize) (int mtu);
-};
-
-struct stmmac_chain_mode_ops {
+struct stmmac_mode_ops {
 	void (*init) (void *des, dma_addr_t phy_addr, unsigned int size,
 		      unsigned int extend_desc);
 	unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
 	unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum);
+	int (*set_16kib_bfsize)(int mtu);
+	void (*init_desc3)(struct dma_desc *p);
 	void (*refill_desc3) (void *priv, struct dma_desc *p);
 	void (*clean_desc3) (void *priv, struct dma_desc *p);
 };
@@ -441,8 +434,7 @@
 	const struct stmmac_ops *mac;
 	const struct stmmac_desc_ops *desc;
 	const struct stmmac_dma_ops *dma;
-	const struct stmmac_ring_mode_ops *ring;
-	const struct stmmac_chain_mode_ops *chain;
+	const struct stmmac_mode_ops *mode;
 	const struct stmmac_hwtimestamp *ptp;
 	struct mii_regs mii;	/* MII register Addresses */
 	struct mac_link link;
@@ -460,7 +452,7 @@
 void stmmac_set_mac(void __iomem *ioaddr, bool enable);
 
 void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
-extern const struct stmmac_ring_mode_ops ring_mode_ops;
-extern const struct stmmac_chain_mode_ops chain_mode_ops;
+extern const struct stmmac_mode_ops ring_mode_ops;
+extern const struct stmmac_mode_ops chain_mode_ops;
 
 #endif /* __COMMON_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index a96c7c2..650a4be 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -100,10 +100,9 @@
 {
 	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
 
-	if (unlikely(priv->plat->has_gmac))
-		/* Fill DES3 in case of RING mode */
-		if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
-			p->des3 = p->des2 + BUF_SIZE_8KiB;
+	/* Fill DES3 in case of RING mode */
+	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+		p->des3 = p->des2 + BUF_SIZE_8KiB;
 }
 
 /* In ring mode we need to fill the desc3 because it is used as buffer */
@@ -126,7 +125,7 @@
 	return ret;
 }
 
-const struct stmmac_ring_mode_ops ring_mode_ops = {
+const struct stmmac_mode_ops ring_mode_ops = {
 	.is_jumbo_frm = stmmac_is_jumbo_frm,
 	.jumbo_frm = stmmac_jumbo_frm,
 	.refill_desc3 = stmmac_refill_desc3,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a2e7d2c..8543e1c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -92,8 +92,8 @@
 module_param(tc, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(tc, "DMA threshold control value");
 
-#define DMA_BUFFER_SIZE	BUF_SIZE_4KiB
-static int buf_sz = DMA_BUFFER_SIZE;
+#define	DEFAULT_BUFSIZE	1536
+static int buf_sz = DEFAULT_BUFSIZE;
 module_param(buf_sz, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(buf_sz, "DMA buffer size");
 
@@ -136,8 +136,8 @@
 		dma_rxsize = DMA_RX_SIZE;
 	if (unlikely(dma_txsize < 0))
 		dma_txsize = DMA_TX_SIZE;
-	if (unlikely((buf_sz < DMA_BUFFER_SIZE) || (buf_sz > BUF_SIZE_16KiB)))
-		buf_sz = DMA_BUFFER_SIZE;
+	if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB)))
+		buf_sz = DEFAULT_BUFSIZE;
 	if (unlikely(flow_ctrl > 1))
 		flow_ctrl = FLOW_AUTO;
 	else if (likely(flow_ctrl < 0))
@@ -286,10 +286,25 @@
 
 	/* MAC core supports the EEE feature. */
 	if (priv->dma_cap.eee) {
-		/* Check if the PHY supports EEE */
-		if (phy_init_eee(priv->phydev, 1))
-			goto out;
+		int tx_lpi_timer = priv->tx_lpi_timer;
 
+		/* Check if the PHY supports EEE */
+		if (phy_init_eee(priv->phydev, 1)) {
+			/* To manage at run-time if the EEE cannot be supported
+			 * anymore (for example because the lp caps have been
+			 * changed).
+			 * In that case the driver disable own timers.
+			 */
+			if (priv->eee_active) {
+				pr_debug("stmmac: disable EEE\n");
+				del_timer_sync(&priv->eee_ctrl_timer);
+				priv->hw->mac->set_eee_timer(priv->ioaddr, 0,
+							     tx_lpi_timer);
+			}
+			priv->eee_active = 0;
+			goto out;
+		}
+		/* Activate the EEE and start timers */
 		if (!priv->eee_active) {
 			priv->eee_active = 1;
 			init_timer(&priv->eee_ctrl_timer);
@@ -300,13 +315,13 @@
 
 			priv->hw->mac->set_eee_timer(priv->ioaddr,
 						     STMMAC_DEFAULT_LIT_LS,
-						     priv->tx_lpi_timer);
+						     tx_lpi_timer);
 		} else
 			/* Set HW EEE according to the speed */
 			priv->hw->mac->set_eee_pls(priv->ioaddr,
 						   priv->phydev->link);
 
-		pr_info("stmmac: Energy-Efficient Ethernet initialized\n");
+		pr_debug("stmmac: Energy-Efficient Ethernet initialized\n");
 
 		ret = true;
 	}
@@ -886,10 +901,10 @@
 		ret = BUF_SIZE_8KiB;
 	else if (mtu >= BUF_SIZE_2KiB)
 		ret = BUF_SIZE_4KiB;
-	else if (mtu >= DMA_BUFFER_SIZE)
+	else if (mtu > DEFAULT_BUFSIZE)
 		ret = BUF_SIZE_2KiB;
 	else
-		ret = DMA_BUFFER_SIZE;
+		ret = DEFAULT_BUFSIZE;
 
 	return ret;
 }
@@ -951,9 +966,9 @@
 
 	p->des2 = priv->rx_skbuff_dma[i];
 
-	if ((priv->mode == STMMAC_RING_MODE) &&
+	if ((priv->hw->mode->init_desc3) &&
 	    (priv->dma_buf_sz == BUF_SIZE_16KiB))
-		priv->hw->ring->init_desc3(p);
+		priv->hw->mode->init_desc3(p);
 
 	return 0;
 }
@@ -984,11 +999,8 @@
 	unsigned int bfsize = 0;
 	int ret = -ENOMEM;
 
-	/* Set the max buffer size according to the DESC mode
-	 * and the MTU. Note that RING mode allows 16KiB bsize.
-	 */
-	if (priv->mode == STMMAC_RING_MODE)
-		bfsize = priv->hw->ring->set_16kib_bfsize(dev->mtu);
+	if (priv->hw->mode->set_16kib_bfsize)
+		bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
 
 	if (bfsize < BUF_SIZE_16KiB)
 		bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
@@ -1029,15 +1041,15 @@
 	/* Setup the chained descriptor addresses */
 	if (priv->mode == STMMAC_CHAIN_MODE) {
 		if (priv->extend_desc) {
-			priv->hw->chain->init(priv->dma_erx, priv->dma_rx_phy,
-					      rxsize, 1);
-			priv->hw->chain->init(priv->dma_etx, priv->dma_tx_phy,
-					      txsize, 1);
+			priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy,
+					     rxsize, 1);
+			priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy,
+					     txsize, 1);
 		} else {
-			priv->hw->chain->init(priv->dma_rx, priv->dma_rx_phy,
-					      rxsize, 0);
-			priv->hw->chain->init(priv->dma_tx, priv->dma_tx_phy,
-					      txsize, 0);
+			priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy,
+					     rxsize, 0);
+			priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy,
+					     txsize, 0);
 		}
 	}
 
@@ -1288,7 +1300,7 @@
 					 DMA_TO_DEVICE);
 			priv->tx_skbuff_dma[entry] = 0;
 		}
-		priv->hw->ring->clean_desc3(priv, p);
+		priv->hw->mode->clean_desc3(priv, p);
 
 		if (likely(skb != NULL)) {
 			dev_kfree_skb(skb);
@@ -1705,7 +1717,7 @@
 	priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
 	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
 
-	alloc_dma_desc_resources(priv);
+	ret = alloc_dma_desc_resources(priv);
 	if (ret < 0) {
 		pr_err("%s: DMA descriptors allocation failed\n", __func__);
 		goto dma_desc_error;
@@ -1844,6 +1856,7 @@
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	struct dma_desc *desc, *first;
 	unsigned int nopaged_len = skb_headlen(skb);
+	unsigned int enh_desc = priv->plat->enh_desc;
 
 	if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
 		if (!netif_queue_stopped(dev)) {
@@ -1871,27 +1884,19 @@
 	first = desc;
 
 	/* To program the descriptors according to the size of the frame */
-	if (priv->mode == STMMAC_RING_MODE) {
-		is_jumbo = priv->hw->ring->is_jumbo_frm(skb->len,
-							priv->plat->enh_desc);
-		if (unlikely(is_jumbo))
-			entry = priv->hw->ring->jumbo_frm(priv, skb,
-							  csum_insertion);
-	} else {
-		is_jumbo = priv->hw->chain->is_jumbo_frm(skb->len,
-							 priv->plat->enh_desc);
-		if (unlikely(is_jumbo))
-			entry = priv->hw->chain->jumbo_frm(priv, skb,
-							   csum_insertion);
-	}
+	if (enh_desc)
+		is_jumbo = priv->hw->mode->is_jumbo_frm(skb->len, enh_desc);
+
 	if (likely(!is_jumbo)) {
 		desc->des2 = dma_map_single(priv->device, skb->data,
 					    nopaged_len, DMA_TO_DEVICE);
 		priv->tx_skbuff_dma[entry] = desc->des2;
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len,
 						csum_insertion, priv->mode);
-	} else
+	} else {
 		desc = first;
+		entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
+	}
 
 	for (i = 0; i < nfrags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
@@ -2029,7 +2034,7 @@
 
 			p->des2 = priv->rx_skbuff_dma[entry];
 
-			priv->hw->ring->refill_desc3(priv, p);
+			priv->hw->mode->refill_desc3(priv, p);
 
 			if (netif_msg_rx_status(priv))
 				pr_debug("\trefill entry #%d\n", entry);
@@ -2633,11 +2638,11 @@
 
 	/* To use the chained or ring mode */
 	if (chain_mode) {
-		priv->hw->chain = &chain_mode_ops;
+		priv->hw->mode = &chain_mode_ops;
 		pr_info(" Chain mode enabled\n");
 		priv->mode = STMMAC_CHAIN_MODE;
 	} else {
-		priv->hw->ring = &ring_mode_ops;
+		priv->hw->mode = &ring_mode_ops;
 		pr_info(" Ring mode enabled\n");
 		priv->mode = STMMAC_RING_MODE;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index c61bc72b..8fb32a8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -36,7 +36,7 @@
 #ifdef CONFIG_DWMAC_STI
 	{ .compatible = "st,stih415-dwmac", .data = &sti_gmac_data},
 	{ .compatible = "st,stih416-dwmac", .data = &sti_gmac_data},
-	{ .compatible = "st,stih127-dwmac", .data = &sti_gmac_data},
+	{ .compatible = "st,stid127-dwmac", .data = &sti_gmac_data},
 #endif
 	/* SoC specific glue layers should come before generic bindings */
 	{ .compatible = "st,spear600-gmac"},
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 651087b..ffd4d12 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1164,11 +1164,17 @@
 
 static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_priv *priv)
 {
+	u32 slave_port;
+
+	slave_port = cpsw_get_slave_port(priv, slave->slave_num);
+
 	if (!slave->phy)
 		return;
 	phy_stop(slave->phy);
 	phy_disconnect(slave->phy);
 	slave->phy = NULL;
+	cpsw_ale_control_set(priv->ale, slave_port,
+			     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
 }
 
 static int cpsw_ndo_open(struct net_device *ndev)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 7141a19..d6fce97 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -442,6 +442,8 @@
 	if (!net)
 		return -ENOMEM;
 
+	netif_carrier_off(net);
+
 	net_device_ctx = netdev_priv(net);
 	net_device_ctx->device_ctx = dev;
 	hv_set_drvdata(dev, net);
@@ -473,6 +475,8 @@
 		pr_err("Unable to register netdev.\n");
 		rndis_filter_device_remove(dev);
 		free_netdev(net);
+	} else {
+		schedule_delayed_work(&net_device_ctx->dwork, 0);
 	}
 
 	return ret;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 1084e5d..b54fd25 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -243,6 +243,22 @@
 	return ret;
 }
 
+static void rndis_set_link_state(struct rndis_device *rdev,
+				 struct rndis_request *request)
+{
+	u32 link_status;
+	struct rndis_query_complete *query_complete;
+
+	query_complete = &request->response_msg.msg.query_complete;
+
+	if (query_complete->status == RNDIS_STATUS_SUCCESS &&
+	    query_complete->info_buflen == sizeof(u32)) {
+		memcpy(&link_status, (void *)((unsigned long)query_complete +
+		       query_complete->info_buf_offset), sizeof(u32));
+		rdev->link_state = link_status != 0;
+	}
+}
+
 static void rndis_filter_receive_response(struct rndis_device *dev,
 				       struct rndis_message *resp)
 {
@@ -272,6 +288,10 @@
 		    sizeof(struct rndis_message) + RNDIS_EXT_LEN) {
 			memcpy(&request->response_msg, resp,
 			       resp->msg_len);
+			if (request->request_msg.ndis_msg_type ==
+			    RNDIS_MSG_QUERY && request->request_msg.msg.
+			    query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS)
+				rndis_set_link_state(dev, request);
 		} else {
 			netdev_err(ndev,
 				"rndis response buffer overflow "
@@ -620,7 +640,6 @@
 	ret = rndis_filter_query_device(dev,
 				      RNDIS_OID_GEN_MEDIA_CONNECT_STATUS,
 				      &link_status, &size);
-	dev->link_state = (link_status != 0) ? true : false;
 
 	return ret;
 }
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index ab31544..a30258a 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -546,12 +546,12 @@
 	int rc;
 	unsigned long flags;
 
-	spin_lock(&lp->lock);
+	spin_lock_irqsave(&lp->lock, flags);
 	if  (lp->irq_busy) {
-		spin_unlock(&lp->lock);
+		spin_unlock_irqrestore(&lp->lock, flags);
 		return -EBUSY;
 	}
-	spin_unlock(&lp->lock);
+	spin_unlock_irqrestore(&lp->lock, flags);
 
 	might_sleep();
 
@@ -725,10 +725,11 @@
 static irqreturn_t at86rf230_isr(int irq, void *data)
 {
 	struct at86rf230_local *lp = data;
+	unsigned long flags;
 
-	spin_lock(&lp->lock);
+	spin_lock_irqsave(&lp->lock, flags);
 	lp->irq_busy = 1;
-	spin_unlock(&lp->lock);
+	spin_unlock_irqrestore(&lp->lock, flags);
 
 	schedule_work(&lp->irqwork);
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index a5d2189..1831fb7 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -506,6 +506,9 @@
 static struct lock_class_key macvlan_netdev_xmit_lock_key;
 static struct lock_class_key macvlan_netdev_addr_lock_key;
 
+#define ALWAYS_ON_FEATURES \
+	(NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX)
+
 #define MACVLAN_FEATURES \
 	(NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
@@ -539,7 +542,7 @@
 	dev->state		= (dev->state & ~MACVLAN_STATE_MASK) |
 				  (lowerdev->state & MACVLAN_STATE_MASK);
 	dev->features 		= lowerdev->features & MACVLAN_FEATURES;
-	dev->features		|= NETIF_F_LLTX;
+	dev->features		|= ALWAYS_ON_FEATURES;
 	dev->gso_max_size	= lowerdev->gso_max_size;
 	dev->iflink		= lowerdev->ifindex;
 	dev->hard_header_len	= lowerdev->hard_header_len;
@@ -699,7 +702,7 @@
 	features = netdev_increment_features(vlan->lowerdev->features,
 					     features,
 					     mask);
-	features |= NETIF_F_LLTX;
+	features |= ALWAYS_ON_FEATURES;
 
 	return features;
 }
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 19c9eca..76d96b9 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -164,9 +164,9 @@
  *   of that setting.  Returns the index of the last setting if
  *   none of the others match.
  */
-static inline int phy_find_setting(int speed, int duplex)
+static inline unsigned int phy_find_setting(int speed, int duplex)
 {
-	int idx = 0;
+	unsigned int idx = 0;
 
 	while (idx < ARRAY_SIZE(settings) &&
 	       (settings[idx].speed != speed || settings[idx].duplex != duplex))
@@ -185,7 +185,7 @@
  *   the mask in features.  Returns the index of the last setting
  *   if nothing else matches.
  */
-static inline int phy_find_valid(int idx, u32 features)
+static inline unsigned int phy_find_valid(unsigned int idx, u32 features)
 {
 	while (idx < MAX_NUM_SETTINGS && !(settings[idx].setting & features))
 		idx++;
@@ -204,7 +204,7 @@
 static void phy_sanitize_settings(struct phy_device *phydev)
 {
 	u32 features = phydev->supported;
-	int idx;
+	unsigned int idx;
 
 	/* Sanitize settings based on PHY capabilities */
 	if ((features & SUPPORTED_Autoneg) == 0)
@@ -954,7 +954,8 @@
 	    (phydev->interface == PHY_INTERFACE_MODE_RGMII))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
-		int idx, status;
+		int status;
+		unsigned int idx;
 
 		/* Read phy status to properly get the right settings */
 		status = phy_read_status(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 82514e7..4b970f7 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -916,6 +916,8 @@
 	int err;
 	int lpa;
 	int lpagb = 0;
+	int common_adv;
+	int common_adv_gb = 0;
 
 	/* Update the link, but return if there was an error */
 	err = genphy_update_link(phydev);
@@ -937,7 +939,7 @@
 
 			phydev->lp_advertising =
 				mii_stat1000_to_ethtool_lpa_t(lpagb);
-			lpagb &= adv << 2;
+			common_adv_gb = lpagb & adv << 2;
 		}
 
 		lpa = phy_read(phydev, MII_LPA);
@@ -950,25 +952,25 @@
 		if (adv < 0)
 			return adv;
 
-		lpa &= adv;
+		common_adv = lpa & adv;
 
 		phydev->speed = SPEED_10;
 		phydev->duplex = DUPLEX_HALF;
 		phydev->pause = 0;
 		phydev->asym_pause = 0;
 
-		if (lpagb & (LPA_1000FULL | LPA_1000HALF)) {
+		if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) {
 			phydev->speed = SPEED_1000;
 
-			if (lpagb & LPA_1000FULL)
+			if (common_adv_gb & LPA_1000FULL)
 				phydev->duplex = DUPLEX_FULL;
-		} else if (lpa & (LPA_100FULL | LPA_100HALF)) {
+		} else if (common_adv & (LPA_100FULL | LPA_100HALF)) {
 			phydev->speed = SPEED_100;
 
-			if (lpa & LPA_100FULL)
+			if (common_adv & LPA_100FULL)
 				phydev->duplex = DUPLEX_FULL;
 		} else
-			if (lpa & LPA_10FULL)
+			if (common_adv & LPA_10FULL)
 				phydev->duplex = DUPLEX_FULL;
 
 		if (phydev->duplex == DUPLEX_FULL) {
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8fe9cb7..26f8635 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1686,7 +1686,9 @@
 				   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 				   NETIF_F_HW_VLAN_STAG_TX;
 		dev->features = dev->hw_features;
-		dev->vlan_features = dev->features;
+		dev->vlan_features = dev->features &
+				     ~(NETIF_F_HW_VLAN_CTAG_TX |
+				       NETIF_F_HW_VLAN_STAG_TX);
 
 		INIT_LIST_HEAD(&tun->disabled);
 		err = tun_attach(tun, file, false);
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index 433f0a0..e2797f1 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -11,7 +11,7 @@
 obj-$(CONFIG_USB_NET_AX8817X)	+= asix.o
 asix-y := asix_devices.o asix_common.o ax88172a.o
 obj-$(CONFIG_USB_NET_AX88179_178A)      += ax88179_178a.o
-obj-$(CONFIG_USB_NET_CDCETHER)	+= cdc_ether.o r815x.o
+obj-$(CONFIG_USB_NET_CDCETHER)	+= cdc_ether.o
 obj-$(CONFIG_USB_NET_CDC_EEM)	+= cdc_eem.o
 obj-$(CONFIG_USB_NET_DM9601)	+= dm9601.o
 obj-$(CONFIG_USB_NET_SR9700)	+= sr9700.o
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 955df81..054e59c 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1029,20 +1029,12 @@
 	dev->mii.phy_id = 0x03;
 	dev->mii.supports_gmii = 1;
 
-	if (usb_device_no_sg_constraint(dev->udev))
-		dev->can_dma_sg = 1;
-
 	dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			      NETIF_F_RXCSUM;
 
 	dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 				 NETIF_F_RXCSUM;
 
-	if (dev->can_dma_sg) {
-		dev->net->features |= NETIF_F_SG | NETIF_F_TSO;
-		dev->net->hw_features |= NETIF_F_SG | NETIF_F_TSO;
-	}
-
 	/* Enable checksum offload */
 	*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
 	       AX_RXCOE_TCPV6 | AX_RXCOE_UDPV6;
@@ -1395,6 +1387,19 @@
 	.tx_fixup = ax88179_tx_fixup,
 };
 
+static const struct driver_info dlink_dub1312_info = {
+	.description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter",
+	.bind = ax88179_bind,
+	.unbind = ax88179_unbind,
+	.status = ax88179_status,
+	.link_reset = ax88179_link_reset,
+	.reset = ax88179_reset,
+	.stop = ax88179_stop,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.rx_fixup = ax88179_rx_fixup,
+	.tx_fixup = ax88179_tx_fixup,
+};
+
 static const struct driver_info sitecom_info = {
 	.description = "Sitecom USB 3.0 to Gigabit Adapter",
 	.bind = ax88179_bind,
@@ -1421,6 +1426,19 @@
 	.tx_fixup = ax88179_tx_fixup,
 };
 
+static const struct driver_info lenovo_info = {
+	.description = "Lenovo OneLinkDock Gigabit LAN",
+	.bind = ax88179_bind,
+	.unbind = ax88179_unbind,
+	.status = ax88179_status,
+	.link_reset = ax88179_link_reset,
+	.reset = ax88179_reset,
+	.stop = ax88179_stop,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX,
+	.rx_fixup = ax88179_rx_fixup,
+	.tx_fixup = ax88179_tx_fixup,
+};
+
 static const struct usb_device_id products[] = {
 {
 	/* ASIX AX88179 10/100/1000 */
@@ -1431,6 +1449,10 @@
 	USB_DEVICE(0x0b95, 0x178a),
 	.driver_info = (unsigned long)&ax88178a_info,
 }, {
+	/* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */
+	USB_DEVICE(0x2001, 0x4a00),
+	.driver_info = (unsigned long)&dlink_dub1312_info,
+}, {
 	/* Sitecom USB 3.0 to Gigabit Adapter */
 	USB_DEVICE(0x0df6, 0x0072),
 	.driver_info = (unsigned long)&sitecom_info,
@@ -1438,6 +1460,10 @@
 	/* Samsung USB Ethernet Adapter */
 	USB_DEVICE(0x04e8, 0xa100),
 	.driver_info = (unsigned long)&samsung_info,
+}, {
+	/* Lenovo OneLinkDock Gigabit LAN */
+	USB_DEVICE(0x17ef, 0x304b),
+	.driver_info = (unsigned long)&lenovo_info,
 },
 	{ },
 };
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 42e1769..bd363b2 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -652,6 +652,13 @@
 	.driver_info = 0,
 },
 
+/* Samsung USB Ethernet Adapters */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, 0xa101, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index d89dbe3..adb12f3 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -449,9 +449,6 @@
 #define MCU_TYPE_PLA			0x0100
 #define MCU_TYPE_USB			0x0000
 
-#define REALTEK_USB_DEVICE(vend, prod)	\
-	USB_DEVICE_INTERFACE_CLASS(vend, prod, USB_CLASS_VENDOR_SPEC)
-
 struct rx_desc {
 	__le32 opts1;
 #define RX_LEN_MASK			0x7fff
@@ -2739,6 +2736,12 @@
 	struct net_device *netdev;
 	int ret;
 
+	if (udev->actconfig->desc.bConfigurationValue != 1) {
+		usb_driver_set_configuration(udev, 1);
+		return -ENODEV;
+	}
+
+	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
 		dev_err(&intf->dev, "Out of memory\n");
@@ -2819,9 +2822,9 @@
 
 /* table of devices that work with this driver */
 static struct usb_device_id rtl8152_table[] = {
-	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)},
-	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)},
-	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)},
+	{USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)},
+	{USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)},
+	{USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)},
 	{}
 };
 
diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c
deleted file mode 100644
index f0a8791..0000000
--- a/drivers/net/usb/r815x.c
+++ /dev/null
@@ -1,248 +0,0 @@
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/mii.h>
-#include <linux/usb.h>
-#include <linux/usb/cdc.h>
-#include <linux/usb/usbnet.h>
-
-#define RTL815x_REQT_READ	0xc0
-#define RTL815x_REQT_WRITE	0x40
-#define RTL815x_REQ_GET_REGS	0x05
-#define RTL815x_REQ_SET_REGS	0x05
-
-#define MCU_TYPE_PLA		0x0100
-#define OCP_BASE		0xe86c
-#define BASE_MII		0xa400
-
-#define BYTE_EN_DWORD		0xff
-#define BYTE_EN_WORD		0x33
-#define BYTE_EN_BYTE		0x11
-
-#define R815x_PHY_ID		32
-#define REALTEK_VENDOR_ID	0x0bda
-
-
-static int pla_read_word(struct usb_device *udev, u16 index)
-{
-	int ret;
-	u8 shift = index & 2;
-	__le32 *tmp;
-
-	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	index &= ~3;
-
-	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
-			      RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
-			      index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
-	if (ret < 0)
-		goto out2;
-
-	ret = __le32_to_cpu(*tmp);
-	ret >>= (shift * 8);
-	ret &= 0xffff;
-
-out2:
-	kfree(tmp);
-	return ret;
-}
-
-static int pla_write_word(struct usb_device *udev, u16 index, u32 data)
-{
-	__le32 *tmp;
-	u32 mask = 0xffff;
-	u16 byen = BYTE_EN_WORD;
-	u8 shift = index & 2;
-	int ret;
-
-	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	data &= mask;
-
-	if (shift) {
-		byen <<= shift;
-		mask <<= (shift * 8);
-		data <<= (shift * 8);
-		index &= ~3;
-	}
-
-	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
-			      RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
-			      index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
-	if (ret < 0)
-		goto out3;
-
-	data |= __le32_to_cpu(*tmp) & ~mask;
-	*tmp = __cpu_to_le32(data);
-
-	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
-			      RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE,
-			      index, MCU_TYPE_PLA | byen, tmp, sizeof(*tmp),
-			      500);
-
-out3:
-	kfree(tmp);
-	return ret;
-}
-
-static int ocp_reg_read(struct usbnet *dev, u16 addr)
-{
-	u16 ocp_base, ocp_index;
-	int ret;
-
-	ocp_base = addr & 0xf000;
-	ret = pla_write_word(dev->udev, OCP_BASE, ocp_base);
-	if (ret < 0)
-		goto out;
-
-	ocp_index = (addr & 0x0fff) | 0xb000;
-	ret = pla_read_word(dev->udev, ocp_index);
-
-out:
-	return ret;
-}
-
-static int ocp_reg_write(struct usbnet *dev, u16 addr, u16 data)
-{
-	u16 ocp_base, ocp_index;
-	int ret;
-
-	ocp_base = addr & 0xf000;
-	ret = pla_write_word(dev->udev, OCP_BASE, ocp_base);
-	if (ret < 0)
-		goto out1;
-
-	ocp_index = (addr & 0x0fff) | 0xb000;
-	ret = pla_write_word(dev->udev, ocp_index, data);
-
-out1:
-	return ret;
-}
-
-static int r815x_mdio_read(struct net_device *netdev, int phy_id, int reg)
-{
-	struct usbnet *dev = netdev_priv(netdev);
-	int ret;
-
-	if (phy_id != R815x_PHY_ID)
-		return -EINVAL;
-
-	if (usb_autopm_get_interface(dev->intf) < 0)
-		return -ENODEV;
-
-	ret = ocp_reg_read(dev, BASE_MII + reg * 2);
-
-	usb_autopm_put_interface(dev->intf);
-	return ret;
-}
-
-static
-void r815x_mdio_write(struct net_device *netdev, int phy_id, int reg, int val)
-{
-	struct usbnet *dev = netdev_priv(netdev);
-
-	if (phy_id != R815x_PHY_ID)
-		return;
-
-	if (usb_autopm_get_interface(dev->intf) < 0)
-		return;
-
-	ocp_reg_write(dev, BASE_MII + reg * 2, val);
-
-	usb_autopm_put_interface(dev->intf);
-}
-
-static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
-{
-	int status;
-
-	status = usbnet_cdc_bind(dev, intf);
-	if (status < 0)
-		return status;
-
-	dev->mii.dev = dev->net;
-	dev->mii.mdio_read = r815x_mdio_read;
-	dev->mii.mdio_write = r815x_mdio_write;
-	dev->mii.phy_id_mask = 0x3f;
-	dev->mii.reg_num_mask = 0x1f;
-	dev->mii.phy_id = R815x_PHY_ID;
-	dev->mii.supports_gmii = 1;
-
-	return status;
-}
-
-static int r8152_bind(struct usbnet *dev, struct usb_interface *intf)
-{
-	int status;
-
-	status = usbnet_cdc_bind(dev, intf);
-	if (status < 0)
-		return status;
-
-	dev->mii.dev = dev->net;
-	dev->mii.mdio_read = r815x_mdio_read;
-	dev->mii.mdio_write = r815x_mdio_write;
-	dev->mii.phy_id_mask = 0x3f;
-	dev->mii.reg_num_mask = 0x1f;
-	dev->mii.phy_id = R815x_PHY_ID;
-	dev->mii.supports_gmii = 0;
-
-	return status;
-}
-
-static const struct driver_info r8152_info = {
-	.description =	"RTL8152 ECM Device",
-	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
-	.bind =		r8152_bind,
-	.unbind =	usbnet_cdc_unbind,
-	.status =	usbnet_cdc_status,
-	.manage_power =	usbnet_manage_power,
-};
-
-static const struct driver_info r8153_info = {
-	.description =	"RTL8153 ECM Device",
-	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
-	.bind =		r8153_bind,
-	.unbind =	usbnet_cdc_unbind,
-	.status =	usbnet_cdc_status,
-	.manage_power =	usbnet_manage_power,
-};
-
-static const struct usb_device_id products[] = {
-{
-	USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM,
-			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
-	.driver_info = (unsigned long) &r8152_info,
-},
-
-{
-	USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM,
-			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
-	.driver_info = (unsigned long) &r8153_info,
-},
-
-	{ },		/* END */
-};
-MODULE_DEVICE_TABLE(usb, products);
-
-static struct usb_driver r815x_driver = {
-	.name =		"r815x",
-	.id_table =	products,
-	.probe =	usbnet_probe,
-	.disconnect =	usbnet_disconnect,
-	.suspend =	usbnet_suspend,
-	.resume =	usbnet_resume,
-	.reset_resume =	usbnet_resume,
-	.supports_autosuspend = 1,
-	.disable_hub_initiated_lpm = 1,
-};
-
-module_usb_driver(r815x_driver);
-
-MODULE_AUTHOR("Hayes Wang");
-MODULE_DESCRIPTION("Realtek USB ECM device");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 2ec2041..5b37437 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -285,7 +285,8 @@
 	dev->ethtool_ops = &veth_ethtool_ops;
 	dev->features |= NETIF_F_LLTX;
 	dev->features |= VETH_FEATURES;
-	dev->vlan_features = dev->features;
+	dev->vlan_features = dev->features &
+			     ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX);
 	dev->destructor = veth_dev_free;
 
 	dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d75f8ed..5632a99 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1711,7 +1711,8 @@
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
 		vi->big_packets = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 3be786f..0fa3b44 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1762,11 +1762,20 @@
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
-	if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
-		vmxnet3_disable_all_intrs(adapter);
-
-	vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size);
-	vmxnet3_enable_all_intrs(adapter);
+	switch (adapter->intr.type) {
+#ifdef CONFIG_PCI_MSI
+	case VMXNET3_IT_MSIX: {
+		int i;
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			vmxnet3_msix_rx(0, &adapter->rx_queue[i]);
+		break;
+	}
+#endif
+	case VMXNET3_IT_MSI:
+	default:
+		vmxnet3_intr(0, adapter->netdev);
+		break;
+	}
 
 }
 #endif	/* CONFIG_NET_POLL_CONTROLLER */
diff --git a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
index 1cc1356..1b6b4d0 100644
--- a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
@@ -57,7 +57,7 @@
 	{0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3236605e, 0x32365a5e},
 	{0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c},
-	{0x00009e20, 0x000003b5, 0x000003b5, 0x000003ce, 0x000003ce},
+	{0x00009e20, 0x000003a5, 0x000003a5, 0x000003a5, 0x000003a5},
 	{0x00009e2c, 0x0000001c, 0x0000001c, 0x00000021, 0x00000021},
 	{0x00009e3c, 0xcf946220, 0xcf946220, 0xcfd5c782, 0xcfd5c282},
 	{0x00009e44, 0x62321e27, 0x62321e27, 0xfe291e27, 0xfe291e27},
@@ -96,7 +96,7 @@
 	{0x0000ae04, 0x001c0000, 0x001c0000, 0x001c0000, 0x00100000},
 	{0x0000ae18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000ae1c, 0x0000019c, 0x0000019c, 0x0000019c, 0x0000019c},
-	{0x0000ae20, 0x000001b5, 0x000001b5, 0x000001ce, 0x000001ce},
+	{0x0000ae20, 0x000001a6, 0x000001a6, 0x000001aa, 0x000001aa},
 	{0x0000b284, 0x00000000, 0x00000000, 0x00000550, 0x00000550},
 };
 
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 11eab9f..303ce27 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1534,7 +1534,7 @@
 bool ath9k_hw_check_alive(struct ath_hw *ah)
 {
 	int count = 50;
-	u32 reg;
+	u32 reg, last_val;
 
 	if (AR_SREV_9300(ah))
 		return !ath9k_hw_detect_mac_hang(ah);
@@ -1542,9 +1542,13 @@
 	if (AR_SREV_9285_12_OR_LATER(ah))
 		return true;
 
+	last_val = REG_READ(ah, AR_OBS_BUS_1);
 	do {
 		reg = REG_READ(ah, AR_OBS_BUS_1);
+		if (reg != last_val)
+			return true;
 
+		last_val = reg;
 		if ((reg & 0x7E7FFFEF) == 0x00702400)
 			continue;
 
@@ -1556,6 +1560,8 @@
 		default:
 			return true;
 		}
+
+		udelay(1);
 	} while (count-- > 0);
 
 	return false;
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index a0ebdd0..82e340d 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -732,11 +732,18 @@
 			return NULL;
 
 		/*
-		 * mark descriptor as zero-length and set the 'more'
-		 * flag to ensure that both buffers get discarded
+		 * Re-check previous descriptor, in case it has been filled
+		 * in the mean time.
 		 */
-		rs->rs_datalen = 0;
-		rs->rs_more = true;
+		ret = ath9k_hw_rxprocdesc(ah, ds, rs);
+		if (ret == -EINPROGRESS) {
+			/*
+			 * mark descriptor as zero-length and set the 'more'
+			 * flag to ensure that both buffers get discarded
+			 */
+			rs->rs_datalen = 0;
+			rs->rs_more = true;
+		}
 	}
 
 	list_del(&bf->list);
@@ -985,32 +992,32 @@
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ieee80211_hdr *hdr;
 	bool discard_current = sc->rx.discard_next;
-	int ret = 0;
 
 	/*
 	 * Discard corrupt descriptors which are marked in
 	 * ath_get_next_rx_buf().
 	 */
-	sc->rx.discard_next = rx_stats->rs_more;
 	if (discard_current)
-		return -EINVAL;
+		goto corrupt;
+
+	sc->rx.discard_next = false;
 
 	/*
 	 * Discard zero-length packets.
 	 */
 	if (!rx_stats->rs_datalen) {
 		RX_STAT_INC(rx_len_err);
-		return -EINVAL;
+		goto corrupt;
 	}
 
-        /*
-         * rs_status follows rs_datalen so if rs_datalen is too large
-         * we can take a hint that hardware corrupted it, so ignore
-         * those frames.
-         */
+	/*
+	 * rs_status follows rs_datalen so if rs_datalen is too large
+	 * we can take a hint that hardware corrupted it, so ignore
+	 * those frames.
+	 */
 	if (rx_stats->rs_datalen > (common->rx_bufsize - ah->caps.rx_status_len)) {
 		RX_STAT_INC(rx_len_err);
-		return -EINVAL;
+		goto corrupt;
 	}
 
 	/* Only use status info from the last fragment */
@@ -1024,10 +1031,8 @@
 	 * This is different from the other corrupt descriptor
 	 * condition handled above.
 	 */
-	if (rx_stats->rs_status & ATH9K_RXERR_CORRUPT_DESC) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	if (rx_stats->rs_status & ATH9K_RXERR_CORRUPT_DESC)
+		goto corrupt;
 
 	hdr = (struct ieee80211_hdr *) (skb->data + ah->caps.rx_status_len);
 
@@ -1043,18 +1048,15 @@
 		if (ath_process_fft(sc, hdr, rx_stats, rx_status->mactime))
 			RX_STAT_INC(rx_spectral);
 
-		ret = -EINVAL;
-		goto exit;
+		return -EINVAL;
 	}
 
 	/*
 	 * everything but the rate is checked here, the rate check is done
 	 * separately to avoid doing two lookups for a rate for each frame.
 	 */
-	if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error)) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error))
+		return -EINVAL;
 
 	if (ath_is_mybeacon(common, hdr)) {
 		RX_STAT_INC(rx_beacons);
@@ -1064,15 +1066,11 @@
 	/*
 	 * This shouldn't happen, but have a safety check anyway.
 	 */
-	if (WARN_ON(!ah->curchan)) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	if (WARN_ON(!ah->curchan))
+		return -EINVAL;
 
-	if (ath9k_process_rate(common, hw, rx_stats, rx_status)) {
-		ret =-EINVAL;
-		goto exit;
-	}
+	if (ath9k_process_rate(common, hw, rx_stats, rx_status))
+		return -EINVAL;
 
 	ath9k_process_rssi(common, hw, rx_stats, rx_status);
 
@@ -1087,9 +1085,11 @@
 		sc->rx.num_pkts++;
 #endif
 
-exit:
-	sc->rx.discard_next = false;
-	return ret;
+	return 0;
+
+corrupt:
+	sc->rx.discard_next = rx_stats->rs_more;
+	return -EINVAL;
 }
 
 static void ath9k_rx_skb_postprocess(struct ath_common *common,
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 0a75e2f..f042a18 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1444,14 +1444,16 @@
 	for (tidno = 0, tid = &an->tid[tidno];
 	     tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
 
-		if (!tid->sched)
-			continue;
-
 		ac = tid->ac;
 		txq = ac->txq;
 
 		ath_txq_lock(sc, txq);
 
+		if (!tid->sched) {
+			ath_txq_unlock(sc, txq);
+			continue;
+		}
+
 		buffered = ath_tid_has_buffered(tid);
 
 		tid->sched = false;
@@ -2184,14 +2186,15 @@
 		txq->stopped = true;
 	}
 
+	if (txctl->an)
+		tid = ath_get_skb_tid(sc, txctl->an, skb);
+
 	if (info->flags & IEEE80211_TX_CTL_PS_RESPONSE) {
 		ath_txq_unlock(sc, txq);
 		txq = sc->tx.uapsdq;
 		ath_txq_lock(sc, txq);
 	} else if (txctl->an &&
 		   ieee80211_is_data_present(hdr->frame_control)) {
-		tid = ath_get_skb_tid(sc, txctl->an, skb);
-
 		WARN_ON(tid->ac->txq != txctl->txq);
 
 		if (info->flags & IEEE80211_TX_CTL_CLEAR_PS_FILT)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
index 3e99189..119ee6e 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
@@ -457,7 +457,6 @@
 
 	u8 tx_hdrlen;		/* sdio bus header length for tx packet */
 	bool txglom;		/* host tx glomming enable flag */
-	struct sk_buff *txglom_sgpad;	/* scatter-gather padding buffer */
 	u16 head_align;		/* buffer pointer alignment */
 	u16 sgentry_align;	/* scatter-gather buffer alignment */
 };
@@ -1944,9 +1943,8 @@
 	if (lastfrm && chain_pad)
 		tail_pad += blksize - chain_pad;
 	if (skb_tailroom(pkt) < tail_pad && pkt->len > blksize) {
-		pkt_pad = bus->txglom_sgpad;
-		if (pkt_pad == NULL)
-			  brcmu_pkt_buf_get_skb(tail_pad + tail_chop);
+		pkt_pad = brcmu_pkt_buf_get_skb(tail_pad + tail_chop +
+						bus->head_align);
 		if (pkt_pad == NULL)
 			return -ENOMEM;
 		ret = brcmf_sdio_txpkt_hdalign(bus, pkt_pad);
@@ -1957,6 +1955,7 @@
 		       tail_chop);
 		*(u32 *)(pkt_pad->cb) = ALIGN_SKB_FLAG + tail_chop;
 		skb_trim(pkt, pkt->len - tail_chop);
+		skb_trim(pkt_pad, tail_pad + tail_chop);
 		__skb_queue_after(pktq, pkt, pkt_pad);
 	} else {
 		ntail = pkt->data_len + tail_pad -
@@ -2011,7 +2010,7 @@
 			return ret;
 		head_pad = (u16)ret;
 		if (head_pad)
-			memset(pkt_next->data, 0, head_pad + bus->tx_hdrlen);
+			memset(pkt_next->data + bus->tx_hdrlen, 0, head_pad);
 
 		total_len += pkt_next->len;
 
@@ -3486,10 +3485,6 @@
 		bus->txglom = false;
 		value = 1;
 		pad_size = bus->sdiodev->func[2]->cur_blksize << 1;
-		bus->txglom_sgpad = brcmu_pkt_buf_get_skb(pad_size);
-		if (!bus->txglom_sgpad)
-			brcmf_err("allocating txglom padding skb failed, reduced performance\n");
-
 		err = brcmf_iovar_data_set(bus->sdiodev->dev, "bus:rxglom",
 					   &value, sizeof(u32));
 		if (err < 0) {
@@ -4053,7 +4048,6 @@
 			brcmf_sdio_chip_detach(&bus->ci);
 		}
 
-		brcmu_pkt_buf_free_skb(bus->txglom_sgpad);
 		kfree(bus->rxbuf);
 		kfree(bus->hdrbuf);
 		kfree(bus);
diff --git a/drivers/net/wireless/hostap/hostap_ap.c b/drivers/net/wireless/hostap/hostap_ap.c
index d36e252..5965255 100644
--- a/drivers/net/wireless/hostap/hostap_ap.c
+++ b/drivers/net/wireless/hostap/hostap_ap.c
@@ -147,7 +147,7 @@
 
 	if (!sta->ap && sta->u.sta.challenge)
 		kfree(sta->u.sta.challenge);
-	del_timer(&sta->timer);
+	del_timer_sync(&sta->timer);
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
 	kfree(sta);
diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index c0d070c..9cdd91c 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -590,6 +590,7 @@
 			sizeof(priv->tid_data[sta_id][tid]));
 
 	priv->stations[sta_id].used &= ~IWL_STA_DRIVER_ACTIVE;
+	priv->stations[sta_id].used &= ~IWL_STA_UCODE_INPROGRESS;
 
 	priv->num_stations--;
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index a6839df..398dd09 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -1291,8 +1291,6 @@
 	struct iwl_compressed_ba_resp *ba_resp = (void *)pkt->data;
 	struct iwl_ht_agg *agg;
 	struct sk_buff_head reclaimed_skbs;
-	struct ieee80211_tx_info *info;
-	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb;
 	int sta_id;
 	int tid;
@@ -1379,22 +1377,28 @@
 	freed = 0;
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
-		hdr = (struct ieee80211_hdr *)skb->data;
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 		if (ieee80211_is_data_qos(hdr->frame_control))
 			freed++;
 		else
 			WARN_ON_ONCE(1);
 
-		info = IEEE80211_SKB_CB(skb);
 		iwl_trans_free_tx_cmd(priv->trans, info->driver_data[1]);
 
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+
 		if (freed == 1) {
 			/* this is the first skb we deliver in this batch */
 			/* put the rate scaling data there */
 			info = IEEE80211_SKB_CB(skb);
 			memset(&info->status, 0, sizeof(info->status));
-			info->flags |= IEEE80211_TX_STAT_ACK;
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			info->status.ampdu_ack_len = ba_resp->txed_2_done;
 			info->status.ampdu_len = ba_resp->txed;
diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
index 76cde6c..18a895a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
@@ -872,8 +872,11 @@
 
 	lockdep_assert_held(&mvm->mutex);
 
-	/* Rssi update while not associated ?! */
-	if (WARN_ON_ONCE(mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT))
+	/*
+	 * Rssi update while not associated - can happen since the statistics
+	 * are handled asynchronously
+	 */
+	if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT)
 		return;
 
 	/* No BT - reports should be disabled */
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index e4ead86..2b0ba1f 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -152,7 +152,7 @@
 	IWL_POWER_SCHEME_LP
 };
 
-#define IWL_CONN_MAX_LISTEN_INTERVAL	70
+#define IWL_CONN_MAX_LISTEN_INTERVAL	10
 #define IWL_UAPSD_AC_INFO		(IEEE80211_WMM_IE_STA_QOSINFO_AC_VO |\
 					 IEEE80211_WMM_IE_STA_QOSINFO_AC_VI |\
 					 IEEE80211_WMM_IE_STA_QOSINFO_AC_BK |\
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 4df12fa..76ee486 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -822,16 +822,12 @@
 	struct iwl_mvm_ba_notif *ba_notif = (void *)pkt->data;
 	struct sk_buff_head reclaimed_skbs;
 	struct iwl_mvm_tid_data *tid_data;
-	struct ieee80211_tx_info *info;
 	struct ieee80211_sta *sta;
 	struct iwl_mvm_sta *mvmsta;
-	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb;
 	int sta_id, tid, freed;
-
 	/* "flow" corresponds to Tx queue */
 	u16 scd_flow = le16_to_cpu(ba_notif->scd_flow);
-
 	/* "ssn" is start of block-ack Tx window, corresponds to index
 	 * (in Tx queue's circular buffer) of first TFD/frame in window */
 	u16 ba_resp_scd_ssn = le16_to_cpu(ba_notif->scd_ssn);
@@ -888,22 +884,26 @@
 	freed = 0;
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
-		hdr = (struct ieee80211_hdr *)skb->data;
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 		if (ieee80211_is_data_qos(hdr->frame_control))
 			freed++;
 		else
 			WARN_ON_ONCE(1);
 
-		info = IEEE80211_SKB_CB(skb);
 		iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]);
 
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+
 		if (freed == 1) {
 			/* this is the first skb we deliver in this batch */
 			/* put the rate scaling data there */
-			info = IEEE80211_SKB_CB(skb);
-			memset(&info->status, 0, sizeof(info->status));
-			info->flags |= IEEE80211_TX_STAT_ACK;
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			info->status.ampdu_ack_len = ba_notif->txed_2_done;
 			info->status.ampdu_len = ba_notif->txed;
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index f47bcbe..3872ead 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -359,13 +359,12 @@
 /* 7265 Series */
 	{IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5110, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5112, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5100, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x510A, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 32f7500..cb6d189 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -621,7 +621,7 @@
 			id = *pos++;
 			elen = *pos++;
 			left -= 2;
-			if (elen > left || elen == 0) {
+			if (elen > left) {
 				lbs_deb_scan("scan response: invalid IE fmt\n");
 				goto done;
 			}
diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c
index 5e0eec4..5d9a808 100644
--- a/drivers/net/wireless/mwifiex/11ac.c
+++ b/drivers/net/wireless/mwifiex/11ac.c
@@ -189,8 +189,7 @@
 		vht_cap->header.len  =
 				cpu_to_le16(sizeof(struct ieee80211_vht_cap));
 		memcpy((u8 *)vht_cap + sizeof(struct mwifiex_ie_types_header),
-		       (u8 *)bss_desc->bcn_vht_cap +
-		       sizeof(struct ieee_types_header),
+		       (u8 *)bss_desc->bcn_vht_cap,
 		       le16_to_cpu(vht_cap->header.len));
 
 		mwifiex_fill_vht_cap_tlv(priv, vht_cap, bss_desc->bss_band);
diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c
index 6261f8c..7db1a89 100644
--- a/drivers/net/wireless/mwifiex/11n.c
+++ b/drivers/net/wireless/mwifiex/11n.c
@@ -308,8 +308,7 @@
 		ht_cap->header.len =
 				cpu_to_le16(sizeof(struct ieee80211_ht_cap));
 		memcpy((u8 *) ht_cap + sizeof(struct mwifiex_ie_types_header),
-		       (u8 *) bss_desc->bcn_ht_cap +
-		       sizeof(struct ieee_types_header),
+		       (u8 *)bss_desc->bcn_ht_cap,
 		       le16_to_cpu(ht_cap->header.len));
 
 		mwifiex_fill_cap_info(priv, radio_type, ht_cap);
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 03688aa..7fe7b53 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -1211,6 +1211,12 @@
 		rd_index = card->rxbd_rdptr & reg->rx_mask;
 		skb_data = card->rx_buf_list[rd_index];
 
+		/* If skb allocation was failed earlier for Rx packet,
+		 * rx_buf_list[rd_index] would have been left with a NULL.
+		 */
+		if (!skb_data)
+			return -ENOMEM;
+
 		MWIFIEX_SKB_PACB(skb_data, &buf_pa);
 		pci_unmap_single(card->dev, buf_pa, MWIFIEX_RX_DATA_BUF_SIZE,
 				 PCI_DMA_FROMDEVICE);
@@ -1525,6 +1531,14 @@
 		if (adapter->ps_state == PS_STATE_SLEEP_CFM) {
 			mwifiex_process_sleep_confirm_resp(adapter, skb->data,
 							   skb->len);
+			mwifiex_pcie_enable_host_int(adapter);
+			if (mwifiex_write_reg(adapter,
+					      PCIE_CPU_INT_EVENT,
+					      CPU_INTR_SLEEP_CFM_DONE)) {
+				dev_warn(adapter->dev,
+					 "Write register failed\n");
+				return -1;
+			}
 			while (reg->sleep_cookie && (count++ < 10) &&
 			       mwifiex_pcie_ok_to_access_hw(adapter))
 				usleep_range(50, 60);
@@ -1993,23 +2007,9 @@
 		adapter->int_status |= pcie_ireg;
 		spin_unlock_irqrestore(&adapter->int_lock, flags);
 
-		if (pcie_ireg & HOST_INTR_CMD_DONE) {
-			if ((adapter->ps_state == PS_STATE_SLEEP_CFM) ||
-			    (adapter->ps_state == PS_STATE_SLEEP)) {
-				mwifiex_pcie_enable_host_int(adapter);
-				if (mwifiex_write_reg(adapter,
-						      PCIE_CPU_INT_EVENT,
-						      CPU_INTR_SLEEP_CFM_DONE)
-						      ) {
-					dev_warn(adapter->dev,
-						 "Write register failed\n");
-					return;
-
-				}
-			}
-		} else if (!adapter->pps_uapsd_mode &&
-			   adapter->ps_state == PS_STATE_SLEEP &&
-			   mwifiex_pcie_ok_to_access_hw(adapter)) {
+		if (!adapter->pps_uapsd_mode &&
+		    adapter->ps_state == PS_STATE_SLEEP &&
+		    mwifiex_pcie_ok_to_access_hw(adapter)) {
 				/* Potentially for PCIe we could get other
 				 * interrupts like shared. Don't change power
 				 * state until cookie is set */
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 0a8a26e..668547c 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -2101,12 +2101,12 @@
 			 curr_bss->ht_info_offset);
 
 	if (curr_bss->bcn_vht_cap)
-		curr_bss->bcn_ht_cap = (void *)(curr_bss->beacon_buf +
-						curr_bss->vht_cap_offset);
+		curr_bss->bcn_vht_cap = (void *)(curr_bss->beacon_buf +
+						 curr_bss->vht_cap_offset);
 
 	if (curr_bss->bcn_vht_oper)
-		curr_bss->bcn_ht_oper = (void *)(curr_bss->beacon_buf +
-						 curr_bss->vht_info_offset);
+		curr_bss->bcn_vht_oper = (void *)(curr_bss->beacon_buf +
+						  curr_bss->vht_info_offset);
 
 	if (curr_bss->bcn_bss_co_2040)
 		curr_bss->bcn_bss_co_2040 =
diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c
index e8ebbd4..2087488 100644
--- a/drivers/net/wireless/mwifiex/usb.c
+++ b/drivers/net/wireless/mwifiex/usb.c
@@ -22,8 +22,6 @@
 
 #define USB_VERSION	"1.0"
 
-static const char usbdriver_name[] = "usb8xxx";
-
 static struct mwifiex_if_ops usb_ops;
 static struct semaphore add_remove_card_sem;
 static struct usb_card_rec *usb_card;
@@ -527,13 +525,6 @@
 						   MWIFIEX_BSS_ROLE_ANY),
 				  MWIFIEX_ASYNC_CMD);
 
-#ifdef CONFIG_PM
-	/* Resume handler may be called due to remote wakeup,
-	 * force to exit suspend anyway
-	 */
-	usb_disable_autosuspend(card->udev);
-#endif /* CONFIG_PM */
-
 	return 0;
 }
 
@@ -567,13 +558,12 @@
 }
 
 static struct usb_driver mwifiex_usb_driver = {
-	.name = usbdriver_name,
+	.name = "mwifiex_usb",
 	.probe = mwifiex_usb_probe,
 	.disconnect = mwifiex_usb_disconnect,
 	.id_table = mwifiex_usb_table,
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
-	.supports_autosuspend = 1,
 };
 
 static int mwifiex_usb_tx_init(struct mwifiex_adapter *adapter)
diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c
index 13eaeed..981cf6e 100644
--- a/drivers/net/wireless/mwifiex/wmm.c
+++ b/drivers/net/wireless/mwifiex/wmm.c
@@ -559,7 +559,8 @@
 	mwifiex_wmm_delete_all_ralist(priv);
 	memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid));
 
-	if (priv->adapter->if_ops.clean_pcie_ring)
+	if (priv->adapter->if_ops.clean_pcie_ring &&
+	    !priv->adapter->surprise_removed)
 		priv->adapter->if_ops.clean_pcie_ring(priv->adapter);
 	spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags);
 }
diff --git a/drivers/net/wireless/ti/wl1251/rx.c b/drivers/net/wireless/ti/wl1251/rx.c
index 123c4bb..cde0eaf 100644
--- a/drivers/net/wireless/ti/wl1251/rx.c
+++ b/drivers/net/wireless/ti/wl1251/rx.c
@@ -180,7 +180,7 @@
 	wl1251_mem_read(wl, rx_packet_ring_addr, rx_buffer, length);
 
 	/* The actual length doesn't include the target's alignment */
-	skb->len = desc->length  - PLCP_HEADER_LENGTH;
+	skb_trim(skb, desc->length - PLCP_HEADER_LENGTH);
 
 	fc = (u16 *)skb->data;
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 7669d49..301cc03 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -132,8 +132,7 @@
 	/* If the skb is GSO then we'll also need an extra slot for the
 	 * metadata.
 	 */
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
-	    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+	if (skb_is_gso(skb))
 		min_slots_needed++;
 
 	/* If the skb can't possibly fit in the remaining slots
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index e5284bc..438d0c0 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -240,7 +240,7 @@
 	struct gnttab_copy *copy_gop;
 	struct xenvif_rx_meta *meta;
 	unsigned long bytes;
-	int gso_type;
+	int gso_type = XEN_NETIF_GSO_TYPE_NONE;
 
 	/* Data must not cross a page boundary. */
 	BUG_ON(size + offset > PAGE_SIZE<<compound_order(page));
@@ -299,12 +299,12 @@
 		}
 
 		/* Leave a gap for the GSO descriptor. */
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
-			gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
-			gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
-		else
-			gso_type = XEN_NETIF_GSO_TYPE_NONE;
+		if (skb_is_gso(skb)) {
+			if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+				gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+			else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+				gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
+		}
 
 		if (*head && ((1 << gso_type) & vif->gso_mask))
 			vif->rx.req_cons++;
@@ -338,19 +338,15 @@
 	int head = 1;
 	int old_meta_prod;
 	int gso_type;
-	int gso_size;
 
 	old_meta_prod = npo->meta_prod;
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
-		gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
-		gso_size = skb_shinfo(skb)->gso_size;
-	} else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
-		gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
-		gso_size = skb_shinfo(skb)->gso_size;
-	} else {
-		gso_type = XEN_NETIF_GSO_TYPE_NONE;
-		gso_size = 0;
+	gso_type = XEN_NETIF_GSO_TYPE_NONE;
+	if (skb_is_gso(skb)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+			gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+			gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
 	}
 
 	/* Set up a GSO prefix descriptor, if necessary */
@@ -358,7 +354,7 @@
 		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
 		meta = npo->meta + npo->meta_prod++;
 		meta->gso_type = gso_type;
-		meta->gso_size = gso_size;
+		meta->gso_size = skb_shinfo(skb)->gso_size;
 		meta->size = 0;
 		meta->id = req->id;
 	}
@@ -368,7 +364,7 @@
 
 	if ((1 << gso_type) & vif->gso_mask) {
 		meta->gso_type = gso_type;
-		meta->gso_size = gso_size;
+		meta->gso_size = skb_shinfo(skb)->gso_size;
 	} else {
 		meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
 		meta->gso_size = 0;
@@ -500,8 +496,9 @@
 			size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
 			max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
 		}
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
-		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+		if (skb_is_gso(skb) &&
+		   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
+		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
 			max_slots_needed++;
 
 		/* If the skb may not fit then bail out now */
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index f9daa9e..e30d800 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -907,6 +907,7 @@
 
 		/* Ethernet work: Delayed to here as it peeks the header. */
 		skb->protocol = eth_type_trans(skb, dev);
+		skb_reset_network_header(skb);
 
 		if (checksum_setup(dev, skb)) {
 			kfree_skb(skb);
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 00660cc..3890166 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -162,8 +162,6 @@
 
 		avail = *r;
 		pci_clip_resource_to_region(bus, &avail, region);
-		if (!resource_size(&avail))
-			continue;
 
 		/*
 		 * "min" is typically PCIBIOS_MIN_IO or PCIBIOS_MIN_MEM to
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6b05f61..fdbc294 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1192,6 +1192,9 @@
 		return err;
 	pci_fixup_device(pci_fixup_enable, dev);
 
+	if (dev->msi_enabled || dev->msix_enabled)
+		return 0;
+
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 	if (pin) {
 		pci_read_config_word(dev, PCI_COMMAND, &cmd);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index be361b7..1e4e693 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -217,7 +217,7 @@
 	select PINCTRL_MXS
 
 config PINCTRL_MSM
-	tristate
+	bool
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
diff --git a/drivers/pinctrl/pinctrl-capri.c b/drivers/pinctrl/pinctrl-capri.c
index 4669c53..eb25002 100644
--- a/drivers/pinctrl/pinctrl-capri.c
+++ b/drivers/pinctrl/pinctrl-capri.c
@@ -1435,7 +1435,7 @@
 }
 
 static struct of_device_id capri_pinctrl_of_match[] = {
-	{ .compatible = "brcm,capri-pinctrl", },
+	{ .compatible = "brcm,bcm11351-pinctrl", },
 	{ },
 };
 
diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c
index 9ccf681..f9fabe9 100644
--- a/drivers/pinctrl/pinctrl-sunxi.c
+++ b/drivers/pinctrl/pinctrl-sunxi.c
@@ -14,6 +14,7 @@
 #include <linux/clk.h>
 #include <linux/gpio.h>
 #include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -584,7 +585,7 @@
 	spin_lock_irqsave(&pctl->lock, flags);
 
 	regval = readl(pctl->membase + reg);
-	regval &= ~IRQ_CFG_IRQ_MASK;
+	regval &= ~(IRQ_CFG_IRQ_MASK << index);
 	writel(regval | (mode << index), pctl->membase + reg);
 
 	spin_unlock_irqrestore(&pctl->lock, flags);
@@ -665,6 +666,7 @@
 
 static void sunxi_pinctrl_irq_handler(unsigned irq, struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_get_chip(irq);
 	struct sunxi_pinctrl *pctl = irq_get_handler_data(irq);
 	const unsigned long reg = readl(pctl->membase + IRQ_STATUS_REG);
 
@@ -674,10 +676,12 @@
 	if (reg) {
 		int irqoffset;
 
+		chained_irq_enter(chip, desc);
 		for_each_set_bit(irqoffset, &reg, SUNXI_IRQ_NUMBER) {
 			int pin_irq = irq_find_mapping(pctl->domain, irqoffset);
 			generic_handle_irq(pin_irq);
 		}
+		chained_irq_exit(chip, desc);
 	}
 }
 
diff --git a/drivers/pinctrl/pinctrl-sunxi.h b/drivers/pinctrl/pinctrl-sunxi.h
index 01c494f..552b0e9 100644
--- a/drivers/pinctrl/pinctrl-sunxi.h
+++ b/drivers/pinctrl/pinctrl-sunxi.h
@@ -511,7 +511,7 @@
 
 static inline u32 sunxi_irq_cfg_reg(u16 irq)
 {
-	u8 reg = irq / IRQ_CFG_IRQ_PER_REG;
+	u8 reg = irq / IRQ_CFG_IRQ_PER_REG * 0x04;
 	return reg + IRQ_CFG_REG;
 }
 
@@ -523,7 +523,7 @@
 
 static inline u32 sunxi_irq_ctrl_reg(u16 irq)
 {
-	u8 reg = irq / IRQ_CTRL_IRQ_PER_REG;
+	u8 reg = irq / IRQ_CTRL_IRQ_PER_REG * 0x04;
 	return reg + IRQ_CTRL_REG;
 }
 
@@ -535,7 +535,7 @@
 
 static inline u32 sunxi_irq_status_reg(u16 irq)
 {
-	u8 reg = irq / IRQ_STATUS_IRQ_PER_REG;
+	u8 reg = irq / IRQ_STATUS_IRQ_PER_REG * 0x04;
 	return reg + IRQ_STATUS_REG;
 }
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 77d103f..567d691 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -89,7 +89,8 @@
 
 	/* GPSR6 */
 	FN_IP13_10, FN_IP13_11, FN_IP13_12, FN_IP13_13, FN_IP13_14,
-	FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19, FN_IP13_22, FN_IP13_24_23,
+	FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19,
+	FN_IP13_22, FN_IP13_24_23, FN_SD1_CLK,
 	FN_IP13_25, FN_IP13_26, FN_IP13_27, FN_IP13_30_28, FN_IP14_1_0,
 	FN_IP14_2, FN_IP14_3, FN_IP14_4, FN_IP14_5, FN_IP14_6, FN_IP14_7,
 	FN_IP14_10_8, FN_IP14_13_11, FN_IP14_16_14, FN_IP14_19_17,
@@ -788,6 +789,7 @@
 	PINMUX_DATA(USB1_PWEN_MARK, FN_USB1_PWEN),
 	PINMUX_DATA(USB1_OVC_MARK, FN_USB1_OVC),
 	PINMUX_DATA(DU0_DOTCLKIN_MARK, FN_DU0_DOTCLKIN),
+	PINMUX_DATA(SD1_CLK_MARK, FN_SD1_CLK),
 
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_0, D0),
@@ -3825,7 +3827,7 @@
 		GP_6_11_FN, FN_IP13_25,
 		GP_6_10_FN, FN_IP13_24_23,
 		GP_6_9_FN, FN_IP13_22,
-		0, 0,
+		GP_6_8_FN, FN_SD1_CLK,
 		GP_6_7_FN, FN_IP13_21_19,
 		GP_6_6_FN, FN_IP13_18_16,
 		GP_6_5_FN, FN_IP13_15,
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index a0d6152..617a491 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -598,7 +598,7 @@
 {
 	struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d);
 
-	if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq))
+	if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE))
 		dev_err(bank->chip.gc.dev,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
@@ -611,7 +611,7 @@
 	struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d);
 
 	sirfsoc_gpio_irq_mask(d);
-	gpio_unlock_as_irq(&bank->chip.gc, d->hwirq);
+	gpio_unlock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE);
 }
 
 static struct irq_chip sirfsoc_irq_chip = {
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 167f3d0..66977eb 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -183,9 +183,7 @@
 	struct resource r = {0};
 	int i, flags;
 
-	if (acpi_dev_resource_memory(res, &r)
-	    || acpi_dev_resource_io(res, &r)
-	    || acpi_dev_resource_address_space(res, &r)
+	if (acpi_dev_resource_address_space(res, &r)
 	    || acpi_dev_resource_ext_address_space(res, &r)) {
 		pnp_add_resource(dev, &r);
 		return AE_OK;
@@ -217,6 +215,17 @@
 	}
 
 	switch (res->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		if (acpi_dev_resource_memory(res, &r))
+			pnp_add_resource(dev, &r);
+		break;
+	case ACPI_RESOURCE_TYPE_IO:
+	case ACPI_RESOURCE_TYPE_FIXED_IO:
+		if (acpi_dev_resource_io(res, &r))
+			pnp_add_resource(dev, &r);
+		break;
 	case ACPI_RESOURCE_TYPE_DMA:
 		dma = &res->data.dma;
 		if (dma->channel_count > 0 && dma->channels[0] != (u8) -1)
diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index 8a843a0..a40b9c3 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -52,8 +52,10 @@
 		offset = pwm_map->output[i];
 
 		/* Return an error if the pin is already assigned */
-		if (test_and_set_bit(offset, &lp3943->pin_used))
+		if (test_and_set_bit(offset, &lp3943->pin_used)) {
+			kfree(pwm_map);
 			return ERR_PTR(-EBUSY);
+		}
 	}
 
 	return pwm_map;
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index b4b0d83..7061ac0 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -678,6 +678,7 @@
 	struct list_head	free_list;
 	dma_cookie_t		completed_cookie;
 	struct tasklet_struct	tasklet;
+	bool			active;
 };
 
 #endif /* CONFIG_RAPIDIO_DMA_ENGINE */
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 502663f..91245f5 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -206,8 +206,8 @@
 {
 	/* Disable BDMA channel interrupts */
 	iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE);
-
-	tasklet_schedule(&bdma_chan->tasklet);
+	if (bdma_chan->active)
+		tasklet_schedule(&bdma_chan->tasklet);
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -562,7 +562,7 @@
 	}
 #endif /* CONFIG_PCI_MSI */
 
-	tasklet_enable(&bdma_chan->tasklet);
+	bdma_chan->active = true;
 	tsi721_bdma_interrupt_enable(bdma_chan, 1);
 
 	return bdma_chan->bd_num - 1;
@@ -576,9 +576,7 @@
 static void tsi721_free_chan_resources(struct dma_chan *dchan)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
 	struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
 	LIST_HEAD(list);
 
 	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
@@ -589,14 +587,25 @@
 	BUG_ON(!list_empty(&bdma_chan->active_list));
 	BUG_ON(!list_empty(&bdma_chan->queue));
 
-	tasklet_disable(&bdma_chan->tasklet);
+	tsi721_bdma_interrupt_enable(bdma_chan, 0);
+	bdma_chan->active = false;
+
+#ifdef CONFIG_PCI_MSI
+	if (priv->flags & TSI721_USING_MSIX) {
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+					   bdma_chan->id].vector);
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT +
+					   bdma_chan->id].vector);
+	} else
+#endif
+	synchronize_irq(priv->pdev->irq);
+
+	tasklet_kill(&bdma_chan->tasklet);
 
 	spin_lock_bh(&bdma_chan->lock);
 	list_splice_init(&bdma_chan->free_list, &list);
 	spin_unlock_bh(&bdma_chan->lock);
 
-	tsi721_bdma_interrupt_enable(bdma_chan, 0);
-
 #ifdef CONFIG_PCI_MSI
 	if (priv->flags & TSI721_USING_MSIX) {
 		free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
@@ -790,6 +799,7 @@
 		bdma_chan->dchan.cookie = 1;
 		bdma_chan->dchan.chan_id = i;
 		bdma_chan->id = i;
+		bdma_chan->active = false;
 
 		spin_lock_init(&bdma_chan->lock);
 
@@ -799,7 +809,6 @@
 
 		tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet,
 			     (unsigned long)bdma_chan);
-		tasklet_disable(&bdma_chan->tasklet);
 		list_add_tail(&bdma_chan->dchan.device_node,
 			      &mport->dma.channels);
 	}
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index d1ac4ca..afca1bc 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -953,6 +953,8 @@
 	return 0;
 }
 
+static int _regulator_do_enable(struct regulator_dev *rdev);
+
 /**
  * set_machine_constraints - sets regulator constraints
  * @rdev: regulator source
@@ -1013,10 +1015,9 @@
 	/* If the constraints say the regulator should be on at this point
 	 * and we have control then make sure it is enabled.
 	 */
-	if ((rdev->constraints->always_on || rdev->constraints->boot_on) &&
-	    ops->enable) {
-		ret = ops->enable(rdev);
-		if (ret < 0) {
+	if (rdev->constraints->always_on || rdev->constraints->boot_on) {
+		ret = _regulator_do_enable(rdev);
+		if (ret < 0 && ret != -EINVAL) {
 			rdev_err(rdev, "failed to enable\n");
 			goto out;
 		}
@@ -1907,8 +1908,6 @@
 
 	trace_regulator_disable_complete(rdev_get_name(rdev));
 
-	_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
-			     NULL);
 	return 0;
 }
 
@@ -1932,6 +1931,8 @@
 				rdev_err(rdev, "failed to disable\n");
 				return ret;
 			}
+			_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
+					NULL);
 		}
 
 		rdev->use_count = 0;
@@ -1984,20 +1985,16 @@
 {
 	int ret = 0;
 
-	/* force disable */
-	if (rdev->desc->ops->disable) {
-		/* ah well, who wants to live forever... */
-		ret = rdev->desc->ops->disable(rdev);
-		if (ret < 0) {
-			rdev_err(rdev, "failed to force disable\n");
-			return ret;
-		}
-		/* notify other consumers that power has been forced off */
-		_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
-			REGULATOR_EVENT_DISABLE, NULL);
+	ret = _regulator_do_disable(rdev);
+	if (ret < 0) {
+		rdev_err(rdev, "failed to force disable\n");
+		return ret;
 	}
 
-	return ret;
+	_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+			REGULATOR_EVENT_DISABLE, NULL);
+
+	return 0;
 }
 
 /**
@@ -3630,23 +3627,18 @@
 
 	mutex_lock(&regulator_list_mutex);
 	list_for_each_entry(rdev, &regulator_list, list) {
-		struct regulator_ops *ops = rdev->desc->ops;
-
 		mutex_lock(&rdev->mutex);
-		if ((rdev->use_count > 0  || rdev->constraints->always_on) &&
-				ops->enable) {
-			error = ops->enable(rdev);
+		if (rdev->use_count > 0  || rdev->constraints->always_on) {
+			error = _regulator_do_enable(rdev);
 			if (error)
 				ret = error;
 		} else {
 			if (!have_full_constraints())
 				goto unlock;
-			if (!ops->disable)
-				goto unlock;
 			if (!_regulator_is_enabled(rdev))
 				goto unlock;
 
-			error = ops->disable(rdev);
+			error = _regulator_do_disable(rdev);
 			if (error)
 				ret = error;
 		}
@@ -3820,7 +3812,7 @@
 		ops = rdev->desc->ops;
 		c = rdev->constraints;
 
-		if (!ops->disable || (c && c->always_on))
+		if (c && c->always_on)
 			continue;
 
 		mutex_lock(&rdev->mutex);
@@ -3841,7 +3833,7 @@
 			/* We log since this may kill the system if it
 			 * goes wrong. */
 			rdev_info(rdev, "disabling\n");
-			ret = ops->disable(rdev);
+			ret = _regulator_do_disable(rdev);
 			if (ret != 0)
 				rdev_err(rdev, "couldn't disable: %d\n", ret);
 		} else {
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 7afd373..c4cde9c 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -580,10 +580,12 @@
 
 	clk_enable(rtc_clk);
 	/* save TICNT for anyone using periodic interrupts */
-	ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
 	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
 		ticnt_en_save = readw(s3c_rtc_base + S3C2410_RTCCON);
 		ticnt_en_save &= S3C64XX_RTCCON_TICEN;
+		ticnt_save = readl(s3c_rtc_base + S3C2410_TICNT);
+	} else {
+		ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
 	}
 	s3c_rtc_enable(pdev, 0);
 
@@ -605,10 +607,15 @@
 
 	clk_enable(rtc_clk);
 	s3c_rtc_enable(pdev, 1);
-	writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX && ticnt_en_save) {
-		tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
-		writew(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON);
+	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
+		writel(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
+		if (ticnt_en_save) {
+			tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
+			writew(tmp | ticnt_en_save,
+					s3c_rtc_base + S3C2410_RTCCON);
+		}
+	} else {
+		writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
 	}
 
 	if (device_may_wakeup(dev) && wake_en) {
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index f6b9188..9f0ea6c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -610,6 +610,7 @@
 		css_wait_for_slow_path();
 		for_each_subchannel_staged(__s390_process_res_acc, NULL,
 					   &link);
+		css_schedule_reprobe();
 	}
 }
 
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index dc542e0..0bc91e4 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -311,7 +311,7 @@
 	} __packed * msg = ap_msg->message;
 
 	int rcblen = CEIL4(xcRB->request_control_blk_length);
-	int replylen;
+	int replylen, req_sumlen, resp_sumlen;
 	char *req_data = ap_msg->message + sizeof(struct type6_hdr) + rcblen;
 	char *function_code;
 
@@ -321,12 +321,34 @@
 		xcRB->request_data_length;
 	if (ap_msg->length > MSGTYPE06_MAX_MSG_SIZE)
 		return -EINVAL;
+
+	/* Overflow check
+	   sum must be greater (or equal) than the largest operand */
+	req_sumlen = CEIL4(xcRB->request_control_blk_length) +
+			xcRB->request_data_length;
+	if ((CEIL4(xcRB->request_control_blk_length) <=
+						xcRB->request_data_length) ?
+		(req_sumlen < xcRB->request_data_length) :
+		(req_sumlen < CEIL4(xcRB->request_control_blk_length))) {
+		return -EINVAL;
+	}
+
 	replylen = sizeof(struct type86_fmt2_msg) +
 		CEIL4(xcRB->reply_control_blk_length) +
 		xcRB->reply_data_length;
 	if (replylen > MSGTYPE06_MAX_MSG_SIZE)
 		return -EINVAL;
 
+	/* Overflow check
+	   sum must be greater (or equal) than the largest operand */
+	resp_sumlen = CEIL4(xcRB->reply_control_blk_length) +
+			xcRB->reply_data_length;
+	if ((CEIL4(xcRB->reply_control_blk_length) <= xcRB->reply_data_length) ?
+		(resp_sumlen < xcRB->reply_data_length) :
+		(resp_sumlen < CEIL4(xcRB->reply_control_blk_length))) {
+		return -EINVAL;
+	}
+
 	/* prepare type6 header */
 	msg->hdr = static_type6_hdrX;
 	memcpy(msg->hdr.agent_id , &(xcRB->agent_ID), sizeof(xcRB->agent_ID));
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c3a83df..795ed61 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1660,7 +1660,6 @@
 				QDIO_FLAG_CLEANUP_USING_CLEAR);
 		if (rc)
 			QETH_CARD_TEXT_(card, 3, "1err%d", rc);
-		qdio_free(CARD_DDEV(card));
 		atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED);
 		break;
 	case QETH_QDIO_CLEANING:
@@ -2605,6 +2604,7 @@
 	return 0;
 out_qdio:
 	qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
+	qdio_free(CARD_DDEV(card));
 	return rc;
 }
 
@@ -4906,9 +4906,11 @@
 	if (retries < 3)
 		QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n",
 			dev_name(&card->gdev->dev));
+	rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
 	ccw_device_set_offline(CARD_DDEV(card));
 	ccw_device_set_offline(CARD_WDEV(card));
 	ccw_device_set_offline(CARD_RDEV(card));
+	qdio_free(CARD_DDEV(card));
 	rc = ccw_device_set_online(CARD_RDEV(card));
 	if (rc)
 		goto retriable;
@@ -4918,7 +4920,6 @@
 	rc = ccw_device_set_online(CARD_DDEV(card));
 	if (rc)
 		goto retriable;
-	rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
 retriable:
 	if (rc == -ERESTARTSYS) {
 		QETH_DBF_TEXT(SETUP, 2, "break1");
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 0710550..908d825 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1091,6 +1091,7 @@
 	ccw_device_set_offline(CARD_DDEV(card));
 	ccw_device_set_offline(CARD_WDEV(card));
 	ccw_device_set_offline(CARD_RDEV(card));
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_RECOVER)
 		card->state = CARD_STATE_RECOVER;
 	else
@@ -1132,6 +1133,7 @@
 		rc = (rc2) ? rc2 : rc3;
 	if (rc)
 		QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_UP)
 		card->state = CARD_STATE_RECOVER;
 	/* let user_space know that device is offline */
@@ -1194,6 +1196,7 @@
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
 	qeth_qdio_clear_card(card, 0);
 	qeth_clear_qdio_buffers(card);
+	qdio_free(CARD_DDEV(card));
 }
 
 static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 0f43042..3524d34 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3447,6 +3447,7 @@
 	ccw_device_set_offline(CARD_DDEV(card));
 	ccw_device_set_offline(CARD_WDEV(card));
 	ccw_device_set_offline(CARD_RDEV(card));
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_RECOVER)
 		card->state = CARD_STATE_RECOVER;
 	else
@@ -3493,6 +3494,7 @@
 		rc = (rc2) ? rc2 : rc3;
 	if (rc)
 		QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+	qdio_free(CARD_DDEV(card));
 	if (recover_flag == CARD_STATE_UP)
 		card->state = CARD_STATE_RECOVER;
 	/* let user_space know that device is offline */
@@ -3545,6 +3547,7 @@
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
 	qeth_qdio_clear_card(card, 0);
 	qeth_clear_qdio_buffers(card);
+	qdio_free(CARD_DDEV(card));
 }
 
 static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev)
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 1f37505..5642a9b 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -325,7 +325,7 @@
 		if (!abrt_task->sc || abrt_task->state == ISCSI_TASK_FREE)
 			continue;
 
-		if (abrt_task->sc->device->lun != abrt_task->sc->device->lun)
+		if (sc->device->lun != abrt_task->sc->device->lun)
 			continue;
 
 		/* Invalidate WRB Posted for this Task */
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index 4911310..22a9bb1 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -311,9 +311,8 @@
 }
 
 #define for_each_isci_host(id, ihost, pdev) \
-	for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \
-	     id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \
-	     ihost = to_pci_info(pdev)->hosts[++id])
+	for (id = 0; id < SCI_MAX_CONTROLLERS && \
+	     (ihost = to_pci_info(pdev)->hosts[id]); id++)
 
 static inline void wait_for_start(struct isci_host *ihost)
 {
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index 85c77f6..ac87974 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -615,13 +615,6 @@
 					  SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION);
 	} else {
 		/* the phy is already the part of the port */
-		u32 port_state = iport->sm.current_state_id;
-
-		/* if the PORT'S state is resetting then the link up is from
-		 * port hard reset in this case, we need to tell the port
-		 * that link up is recieved
-		 */
-		BUG_ON(port_state != SCI_PORT_RESETTING);
 		port_agent->phy_ready_mask |= 1 << phy_index;
 		sci_port_link_up(iport, iphy);
 	}
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 0d30ca8..5d6fda7 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -801,7 +801,7 @@
 		/* XXX: need to cleanup any ireqs targeting this
 		 * domain_device
 		 */
-		ret = TMF_RESP_FUNC_COMPLETE;
+		ret = -ENODEV;
 		goto out;
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index e1fe95e..266724b 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2996,8 +2996,7 @@
 				IS_QLA82XX(ha) || IS_QLA83XX(ha) || \
 				IS_QLA8044(ha))
 #define IS_MSIX_NACK_CAPABLE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
-#define IS_NOPOLLING_TYPE(ha)	((IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
-			IS_QLA83XX(ha)) && (ha)->flags.msix_enabled)
+#define IS_NOPOLLING_TYPE(ha)	(IS_QLA81XX(ha) && (ha)->flags.msix_enabled)
 #define IS_FAC_REQUIRED(ha)	(IS_QLA81XX(ha) || IS_QLA83XX(ha))
 #define IS_NOCACHE_VPD_TYPE(ha)	(IS_QLA81XX(ha) || IS_QLA83XX(ha))
 #define IS_ALOGIO_CAPABLE(ha)	(IS_QLA23XX(ha) || IS_FWI2_CAPABLE(ha))
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 9bc86b9..0a1dcb4 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2880,6 +2880,7 @@
 qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
 #define MIN_MSIX_COUNT	2
+#define ATIO_VECTOR	2
 	int i, ret;
 	struct msix_entry *entries;
 	struct qla_msix_entry *qentry;
@@ -2936,34 +2937,47 @@
 	}
 
 	/* Enable MSI-X vectors for the base queue */
-	for (i = 0; i < ha->msix_count; i++) {
+	for (i = 0; i < 2; i++) {
 		qentry = &ha->msix_entries[i];
-		if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
-			ret = request_irq(qentry->vector,
-				qla83xx_msix_entries[i].handler,
-				0, qla83xx_msix_entries[i].name, rsp);
-		} else if (IS_P3P_TYPE(ha)) {
+		if (IS_P3P_TYPE(ha))
 			ret = request_irq(qentry->vector,
 				qla82xx_msix_entries[i].handler,
 				0, qla82xx_msix_entries[i].name, rsp);
-		} else {
+		else
 			ret = request_irq(qentry->vector,
 				msix_entries[i].handler,
 				0, msix_entries[i].name, rsp);
-		}
-		if (ret) {
-			ql_log(ql_log_fatal, vha, 0x00cb,
-			    "MSI-X: unable to register handler -- %x/%d.\n",
-			    qentry->vector, ret);
-			qla24xx_disable_msix(ha);
-			ha->mqenable = 0;
-			goto msix_out;
-		}
+		if (ret)
+			goto msix_register_fail;
 		qentry->have_irq = 1;
 		qentry->rsp = rsp;
 		rsp->msix = qentry;
 	}
 
+	/*
+	 * If target mode is enable, also request the vector for the ATIO
+	 * queue.
+	 */
+	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
+		qentry = &ha->msix_entries[ATIO_VECTOR];
+		ret = request_irq(qentry->vector,
+			qla83xx_msix_entries[ATIO_VECTOR].handler,
+			0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp);
+		qentry->have_irq = 1;
+		qentry->rsp = rsp;
+		rsp->msix = qentry;
+	}
+
+msix_register_fail:
+	if (ret) {
+		ql_log(ql_log_fatal, vha, 0x00cb,
+		    "MSI-X: unable to register handler -- %x/%d.\n",
+		    qentry->vector, ret);
+		qla24xx_disable_msix(ha);
+		ha->mqenable = 0;
+		goto msix_out;
+	}
+
 	/* Enable MSI-X vector for response queue update for queue 0 */
 	if (IS_QLA83XX(ha)) {
 		if (ha->msixbase && ha->mqiobase &&
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 2eb97d7..0cb7307 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -790,17 +790,32 @@
 }
 
 /* Called by tcm_qla2xxx configfs code */
-void qlt_stop_phase1(struct qla_tgt *tgt)
+int qlt_stop_phase1(struct qla_tgt *tgt)
 {
 	struct scsi_qla_host *vha = tgt->vha;
 	struct qla_hw_data *ha = tgt->ha;
 	unsigned long flags;
 
+	mutex_lock(&qla_tgt_mutex);
+	if (!vha->fc_vport) {
+		struct Scsi_Host *sh = vha->host;
+		struct fc_host_attrs *fc_host = shost_to_fc_host(sh);
+		bool npiv_vports;
+
+		spin_lock_irqsave(sh->host_lock, flags);
+		npiv_vports = (fc_host->npiv_vports_inuse);
+		spin_unlock_irqrestore(sh->host_lock, flags);
+
+		if (npiv_vports) {
+			mutex_unlock(&qla_tgt_mutex);
+			return -EPERM;
+		}
+	}
 	if (tgt->tgt_stop || tgt->tgt_stopped) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04e,
 		    "Already in tgt->tgt_stop or tgt_stopped state\n");
-		dump_stack();
-		return;
+		mutex_unlock(&qla_tgt_mutex);
+		return -EPERM;
 	}
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe003, "Stopping target for host %ld(%p)\n",
@@ -815,6 +830,7 @@
 	qlt_clear_tgt_db(tgt, true);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	mutex_unlock(&vha->vha_tgt.tgt_mutex);
+	mutex_unlock(&qla_tgt_mutex);
 
 	flush_delayed_work(&tgt->sess_del_work);
 
@@ -841,6 +857,7 @@
 
 	/* Wait for sessions to clear out (just in case) */
 	wait_event(tgt->waitQ, test_tgt_sess_count(tgt));
+	return 0;
 }
 EXPORT_SYMBOL(qlt_stop_phase1);
 
@@ -3185,7 +3202,8 @@
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
 		    "SRR cmd %p (se_cmd %p, tag %d, op %x), "
 		    "sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag,
-		    se_cmd->t_task_cdb[0], cmd->sg_cnt, cmd->offset);
+		    se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
+		    cmd->sg_cnt, cmd->offset);
 
 		qlt_handle_srr(vha, sctio, imm);
 
@@ -4181,6 +4199,9 @@
 	tgt->datasegs_per_cmd = QLA_TGT_DATASEGS_PER_CMD_24XX;
 	tgt->datasegs_per_cont = QLA_TGT_DATASEGS_PER_CONT_24XX;
 
+	if (base_vha->fc_vport)
+		return 0;
+
 	mutex_lock(&qla_tgt_mutex);
 	list_add_tail(&tgt->tgt_list_entry, &qla_tgt_glist);
 	mutex_unlock(&qla_tgt_mutex);
@@ -4194,6 +4215,10 @@
 	if (!vha->vha_tgt.qla_tgt)
 		return 0;
 
+	if (vha->fc_vport) {
+		qlt_release(vha->vha_tgt.qla_tgt);
+		return 0;
+	}
 	mutex_lock(&qla_tgt_mutex);
 	list_del(&vha->vha_tgt.qla_tgt->tgt_list_entry);
 	mutex_unlock(&qla_tgt_mutex);
@@ -4265,6 +4290,12 @@
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 			continue;
 		}
+		if (tgt->tgt_stop) {
+			pr_debug("MODE_TARGET in shutdown on qla2xxx(%d)\n",
+				 host->host_no);
+			spin_unlock_irqrestore(&ha->hardware_lock, flags);
+			continue;
+		}
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 		if (!scsi_host_get(host)) {
@@ -4279,12 +4310,11 @@
 			scsi_host_put(host);
 			continue;
 		}
-		mutex_unlock(&qla_tgt_mutex);
-
 		rc = (*callback)(vha, target_lport_ptr, npiv_wwpn, npiv_wwnn);
 		if (rc != 0)
 			scsi_host_put(host);
 
+		mutex_unlock(&qla_tgt_mutex);
 		return rc;
 	}
 	mutex_unlock(&qla_tgt_mutex);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 66e755c..ce33d8c 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -1001,7 +1001,7 @@
 extern void qlt_probe_one_stage1(struct scsi_qla_host *, struct qla_hw_data *);
 extern int qlt_mem_alloc(struct qla_hw_data *);
 extern void qlt_mem_free(struct qla_hw_data *);
-extern void qlt_stop_phase1(struct qla_tgt *);
+extern int qlt_stop_phase1(struct qla_tgt *);
 extern void qlt_stop_phase2(struct qla_tgt *);
 extern irqreturn_t qla83xx_msix_atio_q(int, void *);
 extern void qlt_83xx_iospace_config(struct qla_hw_data *);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 75a141b..788c4fe 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -182,20 +182,6 @@
 	return 0;
 }
 
-static ssize_t tcm_qla2xxx_npiv_format_wwn(char *buf, size_t len,
-					u64 wwpn, u64 wwnn)
-{
-	u8 b[8], b2[8];
-
-	put_unaligned_be64(wwpn, b);
-	put_unaligned_be64(wwnn, b2);
-	return snprintf(buf, len,
-		"%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x,"
-		"%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x",
-		b[0], b[1], b[2], b[3], b[4], b[5], b[6], b[7],
-		b2[0], b2[1], b2[2], b2[3], b2[4], b2[5], b2[6], b2[7]);
-}
-
 static char *tcm_qla2xxx_npiv_get_fabric_name(void)
 {
 	return "qla2xxx_npiv";
@@ -227,15 +213,6 @@
 	return lport->lport_naa_name;
 }
 
-static char *tcm_qla2xxx_npiv_get_fabric_wwn(struct se_portal_group *se_tpg)
-{
-	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
-				struct tcm_qla2xxx_tpg, se_tpg);
-	struct tcm_qla2xxx_lport *lport = tpg->lport;
-
-	return &lport->lport_npiv_name[0];
-}
-
 static u16 tcm_qla2xxx_get_tag(struct se_portal_group *se_tpg)
 {
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
@@ -941,15 +918,41 @@
 			atomic_read(&tpg->lport_tpg_enabled));
 }
 
+static void tcm_qla2xxx_depend_tpg(struct work_struct *work)
+{
+	struct tcm_qla2xxx_tpg *base_tpg = container_of(work,
+				struct tcm_qla2xxx_tpg, tpg_base_work);
+	struct se_portal_group *se_tpg = &base_tpg->se_tpg;
+	struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
+
+	if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
+				  &se_tpg->tpg_group.cg_item)) {
+		atomic_set(&base_tpg->lport_tpg_enabled, 1);
+		qlt_enable_vha(base_vha);
+	}
+	complete(&base_tpg->tpg_base_comp);
+}
+
+static void tcm_qla2xxx_undepend_tpg(struct work_struct *work)
+{
+	struct tcm_qla2xxx_tpg *base_tpg = container_of(work,
+				struct tcm_qla2xxx_tpg, tpg_base_work);
+	struct se_portal_group *se_tpg = &base_tpg->se_tpg;
+	struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
+
+	if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) {
+		atomic_set(&base_tpg->lport_tpg_enabled, 0);
+		configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
+				       &se_tpg->tpg_group.cg_item);
+	}
+	complete(&base_tpg->tpg_base_comp);
+}
+
 static ssize_t tcm_qla2xxx_tpg_store_enable(
 	struct se_portal_group *se_tpg,
 	const char *page,
 	size_t count)
 {
-	struct se_wwn *se_wwn = se_tpg->se_tpg_wwn;
-	struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
-			struct tcm_qla2xxx_lport, lport_wwn);
-	struct scsi_qla_host *vha = lport->qla_vha;
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
 			struct tcm_qla2xxx_tpg, se_tpg);
 	unsigned long op;
@@ -964,19 +967,28 @@
 		pr_err("Illegal value for tpg_enable: %lu\n", op);
 		return -EINVAL;
 	}
+	if (op) {
+		if (atomic_read(&tpg->lport_tpg_enabled))
+			return -EEXIST;
+
+		INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_depend_tpg);
+	} else {
+		if (!atomic_read(&tpg->lport_tpg_enabled))
+			return count;
+
+		INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_undepend_tpg);
+	}
+	init_completion(&tpg->tpg_base_comp);
+	schedule_work(&tpg->tpg_base_work);
+	wait_for_completion(&tpg->tpg_base_comp);
 
 	if (op) {
-		atomic_set(&tpg->lport_tpg_enabled, 1);
-		qlt_enable_vha(vha);
-	} else {
-		if (!vha->vha_tgt.qla_tgt) {
-			pr_err("struct qla_hw_data *vha->vha_tgt.qla_tgt is NULL\n");
+		if (!atomic_read(&tpg->lport_tpg_enabled))
 			return -ENODEV;
-		}
-		atomic_set(&tpg->lport_tpg_enabled, 0);
-		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+	} else {
+		if (atomic_read(&tpg->lport_tpg_enabled))
+			return -EPERM;
 	}
-
 	return count;
 }
 
@@ -1053,11 +1065,64 @@
 	/*
 	 * Clear local TPG=1 pointer for non NPIV mode.
 	 */
-		lport->tpg_1 = NULL;
-
+	lport->tpg_1 = NULL;
 	kfree(tpg);
 }
 
+static ssize_t tcm_qla2xxx_npiv_tpg_show_enable(
+	struct se_portal_group *se_tpg,
+	char *page)
+{
+	return tcm_qla2xxx_tpg_show_enable(se_tpg, page);
+}
+
+static ssize_t tcm_qla2xxx_npiv_tpg_store_enable(
+	struct se_portal_group *se_tpg,
+	const char *page,
+	size_t count)
+{
+	struct se_wwn *se_wwn = se_tpg->se_tpg_wwn;
+	struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
+			struct tcm_qla2xxx_lport, lport_wwn);
+	struct scsi_qla_host *vha = lport->qla_vha;
+	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
+			struct tcm_qla2xxx_tpg, se_tpg);
+	unsigned long op;
+	int rc;
+
+	rc = kstrtoul(page, 0, &op);
+	if (rc < 0) {
+		pr_err("kstrtoul() returned %d\n", rc);
+		return -EINVAL;
+	}
+	if ((op != 1) && (op != 0)) {
+		pr_err("Illegal value for tpg_enable: %lu\n", op);
+		return -EINVAL;
+	}
+	if (op) {
+		if (atomic_read(&tpg->lport_tpg_enabled))
+			return -EEXIST;
+
+		atomic_set(&tpg->lport_tpg_enabled, 1);
+		qlt_enable_vha(vha);
+	} else {
+		if (!atomic_read(&tpg->lport_tpg_enabled))
+			return count;
+
+		atomic_set(&tpg->lport_tpg_enabled, 0);
+		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+	}
+
+	return count;
+}
+
+TF_TPG_BASE_ATTR(tcm_qla2xxx_npiv, enable, S_IRUGO | S_IWUSR);
+
+static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = {
+        &tcm_qla2xxx_npiv_tpg_enable.attr,
+        NULL,
+};
+
 static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
 	struct se_wwn *wwn,
 	struct config_group *group,
@@ -1650,6 +1715,9 @@
 	struct scsi_qla_host *npiv_vha;
 	struct tcm_qla2xxx_lport *lport =
 			(struct tcm_qla2xxx_lport *)target_lport_ptr;
+	struct tcm_qla2xxx_lport *base_lport =
+			(struct tcm_qla2xxx_lport *)base_vha->vha_tgt.target_lport_ptr;
+	struct tcm_qla2xxx_tpg *base_tpg;
 	struct fc_vport_identifiers vport_id;
 
 	if (!qla_tgt_mode_enabled(base_vha)) {
@@ -1657,6 +1725,13 @@
 		return -EPERM;
 	}
 
+	if (!base_lport || !base_lport->tpg_1 ||
+	    !atomic_read(&base_lport->tpg_1->lport_tpg_enabled)) {
+		pr_err("qla2xxx base_lport or tpg_1 not available\n");
+		return -EPERM;
+	}
+	base_tpg = base_lport->tpg_1;
+
 	memset(&vport_id, 0, sizeof(vport_id));
 	vport_id.port_name = npiv_wwpn;
 	vport_id.node_name = npiv_wwnn;
@@ -1675,7 +1750,6 @@
 	npiv_vha = (struct scsi_qla_host *)vport->dd_data;
 	npiv_vha->vha_tgt.target_lport_ptr = target_lport_ptr;
 	lport->qla_vha = npiv_vha;
-
 	scsi_host_get(npiv_vha->host);
 	return 0;
 }
@@ -1714,8 +1788,6 @@
 	}
 	lport->lport_npiv_wwpn = npiv_wwpn;
 	lport->lport_npiv_wwnn = npiv_wwnn;
-	tcm_qla2xxx_npiv_format_wwn(&lport->lport_npiv_name[0],
-			TCM_QLA2XXX_NAMELEN, npiv_wwpn, npiv_wwnn);
 	sprintf(lport->lport_naa_name, "naa.%016llx", (unsigned long long) npiv_wwpn);
 
 	ret = tcm_qla2xxx_init_lport(lport);
@@ -1824,7 +1896,7 @@
 static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
 	.get_fabric_name		= tcm_qla2xxx_npiv_get_fabric_name,
 	.get_fabric_proto_ident		= tcm_qla2xxx_get_fabric_proto_ident,
-	.tpg_get_wwn			= tcm_qla2xxx_npiv_get_fabric_wwn,
+	.tpg_get_wwn			= tcm_qla2xxx_get_fabric_wwn,
 	.tpg_get_tag			= tcm_qla2xxx_get_tag,
 	.tpg_get_default_depth		= tcm_qla2xxx_get_default_depth,
 	.tpg_get_pr_transport_id	= tcm_qla2xxx_get_pr_transport_id,
@@ -1935,7 +2007,7 @@
 	 */
 	npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs =
-	    tcm_qla2xxx_tpg_attrs;
+	    tcm_qla2xxx_npiv_tpg_attrs;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 275d8b9..33aaac8 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -4,8 +4,6 @@
 #define TCM_QLA2XXX_VERSION	"v0.1"
 /* length of ASCII WWPNs including pad */
 #define TCM_QLA2XXX_NAMELEN	32
-/* lenth of ASCII NPIV 'WWPN+WWNN' including pad */
-#define TCM_QLA2XXX_NPIV_NAMELEN 66
 
 #include "qla_target.h"
 
@@ -43,6 +41,9 @@
 	struct tcm_qla2xxx_tpg_attrib tpg_attrib;
 	/* Returned by tcm_qla2xxx_make_tpg() */
 	struct se_portal_group se_tpg;
+	/* Items for dealing with configfs_depend_item */
+	struct completion tpg_base_comp;
+	struct work_struct tpg_base_work;
 };
 
 struct tcm_qla2xxx_fc_loopid {
@@ -62,8 +63,6 @@
 	char lport_name[TCM_QLA2XXX_NAMELEN];
 	/* ASCII formatted naa WWPN for VPD page 83 etc */
 	char lport_naa_name[TCM_QLA2XXX_NAMELEN];
-	/* ASCII formatted WWPN+WWNN for NPIV FC Target Lport */
-	char lport_npiv_name[TCM_QLA2XXX_NPIV_NAMELEN];
 	/* map for fc_port pointers in 24-bit FC Port ID space */
 	struct btree_head32 lport_fcport_map;
 	/* vmalloc-ed memory for fc_port pointers for 16-bit FC loop ID */
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 17d7404..9969fa1 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1419,6 +1419,9 @@
 {
 	struct stor_mem_pools *memp = sdevice->hostdata;
 
+	if (!memp)
+		return;
+
 	mempool_destroy(memp->request_mempool);
 	kmem_cache_destroy(memp->request_pool);
 	kfree(memp);
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index 31534b5..c3b2fb9b 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -132,9 +132,9 @@
 
 		flags = GPIOF_DIR_OUT;
 		if (spi->mode & SPI_CS_HIGH)
-			flags |= GPIOF_INIT_HIGH;
-		else
 			flags |= GPIOF_INIT_LOW;
+		else
+			flags |= GPIOF_INIT_HIGH;
 
 		status = gpio_request_one(cdata->gpio, flags,
 					  dev_name(&spi->dev));
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index b0842f7..5d7b07f 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1455,6 +1455,14 @@
 {
 	struct spi_master	*master = dev_get_drvdata(dev);
 	struct atmel_spi	*as = spi_master_get_devdata(master);
+	int ret;
+
+	/* Stop the queue running */
+	ret = spi_master_suspend(master);
+	if (ret) {
+		dev_warn(dev, "cannot suspend master\n");
+		return ret;
+	}
 
 	clk_disable_unprepare(as->clk);
 	return 0;
@@ -1464,9 +1472,16 @@
 {
 	struct spi_master	*master = dev_get_drvdata(dev);
 	struct atmel_spi	*as = spi_master_get_devdata(master);
+	int ret;
 
 	clk_prepare_enable(as->clk);
-	return 0;
+
+	/* Start the queue running */
+	ret = spi_master_resume(master);
+	if (ret)
+		dev_err(dev, "problem starting queue (%d)\n", ret);
+
+	return ret;
 }
 
 static SIMPLE_DEV_PM_OPS(atmel_spi_pm_ops, atmel_spi_suspend, atmel_spi_resume);
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index cabed8f..28ae470 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -514,7 +514,8 @@
 #ifdef CONFIG_PM_RUNTIME
 static int mcfqspi_runtime_suspend(struct device *dev)
 {
-	struct mcfqspi *mcfqspi = dev_get_drvdata(dev);
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
 
 	clk_disable(mcfqspi->clk);
 
@@ -523,7 +524,8 @@
 
 static int mcfqspi_runtime_resume(struct device *dev)
 {
-	struct mcfqspi *mcfqspi = dev_get_drvdata(dev);
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
 
 	clk_enable(mcfqspi->clk);
 
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index ec79f72..a253920 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -420,7 +420,6 @@
 
 static int dspi_resume(struct device *dev)
 {
-
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
@@ -504,7 +503,7 @@
 	clk_prepare_enable(dspi->clk);
 
 	init_waitqueue_head(&dspi->waitq);
-	platform_set_drvdata(pdev, dspi);
+	platform_set_drvdata(pdev, master);
 
 	ret = spi_bitbang_start(&dspi->bitbang);
 	if (ret != 0) {
@@ -525,7 +524,8 @@
 
 static int dspi_remove(struct platform_device *pdev)
 {
-	struct fsl_dspi *dspi = platform_get_drvdata(pdev);
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
 	/* Disconnect from the SPI framework */
 	spi_bitbang_stop(&dspi->bitbang);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index a5474ef..47f15d9 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -948,8 +948,8 @@
 	spi_bitbang_stop(&spi_imx->bitbang);
 
 	writel(0, spi_imx->base + MXC_CSPICTRL);
-	clk_disable_unprepare(spi_imx->clk_ipg);
-	clk_disable_unprepare(spi_imx->clk_per);
+	clk_unprepare(spi_imx->clk_ipg);
+	clk_unprepare(spi_imx->clk_per);
 	spi_master_put(master);
 
 	return 0;
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index 2e7f38c..88eb57e 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -915,7 +915,7 @@
 	/* Set Tx DMA */
 	param = &dma->param_tx;
 	param->dma_dev = &dma_dev->dev;
-	param->chan_id = data->master->bus_num * 2; /* Tx = 0, 2 */
+	param->chan_id = data->ch * 2; /* Tx = 0, 2 */;
 	param->tx_reg = data->io_base_addr + PCH_SPDWR;
 	param->width = width;
 	chan = dma_request_channel(mask, pch_spi_filter, param);
@@ -930,7 +930,7 @@
 	/* Set Rx DMA */
 	param = &dma->param_rx;
 	param->dma_dev = &dma_dev->dev;
-	param->chan_id = data->master->bus_num * 2 + 1; /* Rx = Tx + 1 */
+	param->chan_id = data->ch * 2 + 1; /* Rx = Tx + 1 */;
 	param->rx_reg = data->io_base_addr + PCH_SPDRR;
 	param->width = width;
 	chan = dma_request_channel(mask, pch_spi_filter, param);
@@ -1452,6 +1452,11 @@
 
 	pch_spi_set_master_mode(master);
 
+	if (use_dma) {
+		dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
+		pch_alloc_dma_buf(board_dat, data);
+	}
+
 	ret = spi_register_master(master);
 	if (ret != 0) {
 		dev_err(&plat_dev->dev,
@@ -1459,14 +1464,10 @@
 		goto err_spi_register_master;
 	}
 
-	if (use_dma) {
-		dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
-		pch_alloc_dma_buf(board_dat, data);
-	}
-
 	return 0;
 
 err_spi_register_master:
+	pch_free_dma_buf(board_dat, data);
 	free_irq(board_dat->pdev->irq, data);
 err_request_irq:
 	pch_spi_free_resources(board_dat, data);
diff --git a/drivers/staging/cxt1e1/linux.c b/drivers/staging/cxt1e1/linux.c
index 4a08e16..79206cb 100644
--- a/drivers/staging/cxt1e1/linux.c
+++ b/drivers/staging/cxt1e1/linux.c
@@ -866,6 +866,8 @@
             _IOC_SIZE (iocmd));
 #endif
     iolen = _IOC_SIZE (iocmd);
+    if (iolen > sizeof(arg))
+        return -EFAULT;
     data = ifr->ifr_data + sizeof (iocmd);
     if (copy_from_user (&arg, data, iolen))
         return -EFAULT;
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index 7fc66a6..514844e 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -757,6 +757,7 @@
 	}
 
 	/* if it is released, wait for the next touch via IRQ */
+	lradc->cur_plate = LRADC_TOUCH;
 	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1);
 	mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1);
 }
diff --git a/drivers/staging/imx-drm/imx-hdmi.c b/drivers/staging/imx-drm/imx-hdmi.c
index 62ce0e8..f996e08 100644
--- a/drivers/staging/imx-drm/imx-hdmi.c
+++ b/drivers/staging/imx-drm/imx-hdmi.c
@@ -1883,7 +1883,6 @@
 	struct drm_connector *connector = &hdmi->connector;
 	struct drm_encoder *encoder = &hdmi->encoder;
 
-	drm_mode_connector_detach_encoder(connector, encoder);
 	imx_drm_remove_connector(hdmi->imx_drm_connector);
 	imx_drm_remove_encoder(hdmi->imx_drm_encoder);
 
diff --git a/drivers/staging/imx-drm/imx-ldb.c b/drivers/staging/imx-drm/imx-ldb.c
index 7e59329..c703e98 100644
--- a/drivers/staging/imx-drm/imx-ldb.c
+++ b/drivers/staging/imx-drm/imx-ldb.c
@@ -595,8 +595,6 @@
 		struct drm_connector *connector = &channel->connector;
 		struct drm_encoder *encoder = &channel->encoder;
 
-		drm_mode_connector_detach_encoder(connector, encoder);
-
 		imx_drm_remove_connector(channel->imx_drm_connector);
 		imx_drm_remove_encoder(channel->imx_drm_encoder);
 	}
diff --git a/drivers/staging/imx-drm/imx-tve.c b/drivers/staging/imx-drm/imx-tve.c
index 9abc7ca..64729fa 100644
--- a/drivers/staging/imx-drm/imx-tve.c
+++ b/drivers/staging/imx-drm/imx-tve.c
@@ -709,8 +709,6 @@
 	struct drm_connector *connector = &tve->connector;
 	struct drm_encoder *encoder = &tve->encoder;
 
-	drm_mode_connector_detach_encoder(connector, encoder);
-
 	imx_drm_remove_connector(tve->imx_drm_connector);
 	imx_drm_remove_encoder(tve->imx_drm_encoder);
 
diff --git a/drivers/staging/imx-drm/parallel-display.c b/drivers/staging/imx-drm/parallel-display.c
index 351d61d..823d015 100644
--- a/drivers/staging/imx-drm/parallel-display.c
+++ b/drivers/staging/imx-drm/parallel-display.c
@@ -244,8 +244,6 @@
 	struct drm_connector *connector = &imxpd->connector;
 	struct drm_encoder *encoder = &imxpd->encoder;
 
-	drm_mode_connector_detach_encoder(connector, encoder);
-
 	imx_drm_remove_connector(imxpd->imx_drm_connector);
 	imx_drm_remove_encoder(imxpd->imx_drm_encoder);
 
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index a70dcef..2f40ff5 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -55,6 +55,7 @@
 	/****** 8188EUS ********/
 	{USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */
 	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
+	{USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
 	{}	/* Terminating entry */
 };
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 7f1a7ce..b83ec37 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -785,7 +785,7 @@
 	spin_unlock_bh(&conn->cmd_lock);
 
 	list_for_each_entry_safe(cmd, cmd_p, &ack_list, i_conn_node) {
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		iscsit_free_cmd(cmd, false);
 	}
 }
@@ -3708,7 +3708,7 @@
 		break;
 	case ISTATE_REMOVE:
 		spin_lock_bh(&conn->cmd_lock);
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_free_cmd(cmd, false);
@@ -4151,7 +4151,7 @@
 	spin_lock_bh(&conn->cmd_lock);
 	list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) {
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_increment_maxcmdsn(cmd, sess);
@@ -4196,6 +4196,10 @@
 	iscsit_stop_timers_for_cmds(conn);
 	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
+
+	if (conn->conn_transport->iscsit_wait_conn)
+		conn->conn_transport->iscsit_wait_conn(conn);
+
 	iscsit_free_queue_reqs_for_conn(conn);
 
 	/*
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 33be1fb..4ca8fd2 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -138,7 +138,7 @@
 		list_for_each_entry_safe(cmd, cmd_tmp,
 				&cr->conn_recovery_cmd_list, i_conn_node) {
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			cmd->conn = NULL;
 			spin_unlock(&cr->conn_recovery_cmd_lock);
 			iscsit_free_cmd(cmd, true);
@@ -160,7 +160,7 @@
 		list_for_each_entry_safe(cmd, cmd_tmp,
 				&cr->conn_recovery_cmd_list, i_conn_node) {
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			cmd->conn = NULL;
 			spin_unlock(&cr->conn_recovery_cmd_lock);
 			iscsit_free_cmd(cmd, true);
@@ -216,7 +216,7 @@
 	}
 	cr = cmd->cr;
 
-	list_del(&cmd->i_conn_node);
+	list_del_init(&cmd->i_conn_node);
 	return --cr->cmd_count;
 }
 
@@ -297,7 +297,7 @@
 		if (!(cmd->cmd_flags & ICF_OOO_CMDSN))
 			continue;
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 
 		spin_unlock_bh(&conn->cmd_lock);
 		iscsit_free_cmd(cmd, true);
@@ -335,7 +335,7 @@
 	/*
 	 * Only perform connection recovery on ISCSI_OP_SCSI_CMD or
 	 * ISCSI_OP_NOOP_OUT opcodes.  For all other opcodes call
-	 * list_del(&cmd->i_conn_node); to release the command to the
+	 * list_del_init(&cmd->i_conn_node); to release the command to the
 	 * session pool and remove it from the connection's list.
 	 *
 	 * Also stop the DataOUT timer, which will be restarted after
@@ -351,7 +351,7 @@
 				" CID: %hu\n", cmd->iscsi_opcode,
 				cmd->init_task_tag, cmd->cmd_sn, conn->cid);
 
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			spin_unlock_bh(&conn->cmd_lock);
 			iscsit_free_cmd(cmd, true);
 			spin_lock_bh(&conn->cmd_lock);
@@ -371,7 +371,7 @@
 		 */
 		if (!(cmd->cmd_flags & ICF_OOO_CMDSN) && !cmd->immediate_cmd &&
 		     iscsi_sna_gte(cmd->cmd_sn, conn->sess->exp_cmd_sn)) {
-			list_del(&cmd->i_conn_node);
+			list_del_init(&cmd->i_conn_node);
 			spin_unlock_bh(&conn->cmd_lock);
 			iscsit_free_cmd(cmd, true);
 			spin_lock_bh(&conn->cmd_lock);
@@ -393,7 +393,7 @@
 
 		cmd->sess = conn->sess;
 
-		list_del(&cmd->i_conn_node);
+		list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_free_all_datain_reqs(cmd);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 3976183..44a5471 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -137,7 +137,7 @@
 	list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) {
 
 		spin_lock(&tpg->tpg_state_lock);
-		if (tpg->tpg_state == TPG_STATE_FREE) {
+		if (tpg->tpg_state != TPG_STATE_ACTIVE) {
 			spin_unlock(&tpg->tpg_state_lock);
 			continue;
 		}
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index a448944..77e6531 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1074,31 +1074,36 @@
 	struct scatterlist *psg;
 	void *paddr, *addr;
 	unsigned int i, len, left;
-	unsigned int offset = 0;
+	unsigned int offset = sg_off;
 
 	left = sectors * dev->prot_length;
 
 	for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) {
-
-		len = min(psg->length, left);
-		if (offset >= sg->length) {
-			sg = sg_next(sg);
-			offset = 0;
-			sg_off = sg->offset;
-		}
+		unsigned int psg_len, copied = 0;
 
 		paddr = kmap_atomic(sg_page(psg)) + psg->offset;
-		addr = kmap_atomic(sg_page(sg)) + sg_off;
+		psg_len = min(left, psg->length);
+		while (psg_len) {
+			len = min(psg_len, sg->length - offset);
+			addr = kmap_atomic(sg_page(sg)) + sg->offset + offset;
 
-		if (read)
-			memcpy(paddr, addr, len);
-		else
-			memcpy(addr, paddr, len);
+			if (read)
+				memcpy(paddr + copied, addr, len);
+			else
+				memcpy(addr, paddr + copied, len);
 
-		left -= len;
-		offset += len;
+			left -= len;
+			offset += len;
+			copied += len;
+			psg_len -= len;
+
+			if (offset >= sg->length) {
+				sg = sg_next(sg);
+				offset = 0;
+			}
+			kunmap_atomic(addr);
+		}
 		kunmap_atomic(paddr);
-		kunmap_atomic(addr);
 	}
 }
 
@@ -1163,7 +1168,7 @@
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_dif_v1_tuple *sdt;
-	struct scatterlist *dsg;
+	struct scatterlist *dsg, *psg = sg;
 	sector_t sector = start;
 	void *daddr, *paddr;
 	int i, j, offset = sg_off;
@@ -1171,14 +1176,14 @@
 
 	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
 		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
-		paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+		paddr = kmap_atomic(sg_page(psg)) + sg->offset;
 
 		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
 
-			if (offset >= sg->length) {
+			if (offset >= psg->length) {
 				kunmap_atomic(paddr);
-				sg = sg_next(sg);
-				paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+				psg = sg_next(psg);
+				paddr = kmap_atomic(sg_page(psg)) + psg->offset;
 				offset = 0;
 			}
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 24b4f65d..2956250 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1601,6 +1601,9 @@
 	case TCM_CHECK_CONDITION_ABORT_CMD:
 	case TCM_CHECK_CONDITION_UNIT_ATTENTION:
 	case TCM_CHECK_CONDITION_NOT_READY:
+	case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
+	case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
+	case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
 		break;
 	case TCM_OUT_OF_RESOURCES:
 		sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 35c0664..5f88d76 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -136,6 +136,7 @@
 config RCAR_THERMAL
 	tristate "Renesas R-Car thermal driver"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enable this to plug the R-Car thermal sensor driver into the Linux
 	  thermal framework.
@@ -210,8 +211,16 @@
 	tristate "ACPI INT3403 thermal driver"
 	depends on X86 && ACPI
 	help
-	  This driver uses ACPI INT3403 device objects. If present, it will
-	  register each INT3403 thermal sensor as a thermal zone.
+	  Newer laptops and tablets that use ACPI may have thermal sensors
+	  outside the core CPU/SOC for thermal safety reasons. These
+	  temperature sensors are also exposed for the OS to use via the so
+	  called INT3403 ACPI object. This driver will, on devices that have
+	  such sensors, expose the temperature information from these sensors
+	  to userspace via the normal thermal framework. This means that a wide
+	  range of applications and GUI widgets can show this information to
+	  the user or use this information for making decisions. For example,
+	  the Intel Thermal Daemon can use this information to allow the user
+	  to select his laptop to run without turning on the fans.
 
 menu "Texas Instruments thermal drivers"
 source "drivers/thermal/ti-soc-thermal/Kconfig"
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 338a88b..71b0ec0 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -56,10 +56,15 @@
 static DEFINE_MUTEX(thermal_list_lock);
 static DEFINE_MUTEX(thermal_governor_lock);
 
+static struct thermal_governor *def_governor;
+
 static struct thermal_governor *__find_governor(const char *name)
 {
 	struct thermal_governor *pos;
 
+	if (!name || !name[0])
+		return def_governor;
+
 	list_for_each_entry(pos, &thermal_governor_list, governor_list)
 		if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
 			return pos;
@@ -82,17 +87,23 @@
 	if (__find_governor(governor->name) == NULL) {
 		err = 0;
 		list_add(&governor->governor_list, &thermal_governor_list);
+		if (!def_governor && !strncmp(governor->name,
+			DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH))
+			def_governor = governor;
 	}
 
 	mutex_lock(&thermal_list_lock);
 
 	list_for_each_entry(pos, &thermal_tz_list, node) {
+		/*
+		 * only thermal zones with specified tz->tzp->governor_name
+		 * may run with tz->govenor unset
+		 */
 		if (pos->governor)
 			continue;
-		if (pos->tzp)
-			name = pos->tzp->governor_name;
-		else
-			name = DEFAULT_THERMAL_GOVERNOR;
+
+		name = pos->tzp->governor_name;
+
 		if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
 			pos->governor = governor;
 	}
@@ -342,8 +353,8 @@
 static void handle_non_critical_trips(struct thermal_zone_device *tz,
 			int trip, enum thermal_trip_type trip_type)
 {
-	if (tz->governor)
-		tz->governor->throttle(tz, trip);
+	tz->governor ? tz->governor->throttle(tz, trip) :
+		       def_governor->throttle(tz, trip);
 }
 
 static void handle_critical_trips(struct thermal_zone_device *tz,
@@ -1107,7 +1118,7 @@
 	INIT_LIST_HEAD(&cdev->thermal_instances);
 	cdev->np = np;
 	cdev->ops = ops;
-	cdev->updated = true;
+	cdev->updated = false;
 	cdev->device.class = &thermal_class;
 	cdev->devdata = devdata;
 	dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
@@ -1533,7 +1544,7 @@
 	if (tz->tzp)
 		tz->governor = __find_governor(tz->tzp->governor_name);
 	else
-		tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR);
+		tz->governor = def_governor;
 
 	mutex_unlock(&thermal_governor_lock);
 
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index 972e1c7..081fd7e 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/x86_pkg_temp_thermal.c
@@ -68,6 +68,10 @@
 	struct thermal_zone_device *tzone;
 };
 
+static const struct thermal_zone_params pkg_temp_tz_params = {
+	.no_hwmon	= true,
+};
+
 /* List maintaining number of package instances */
 static LIST_HEAD(phy_dev_list);
 static DEFINE_MUTEX(phy_dev_list_mutex);
@@ -394,7 +398,6 @@
 	int err;
 	u32 tj_max;
 	struct phy_dev_entry *phy_dev_entry;
-	char buffer[30];
 	int thres_count;
 	u32 eax, ebx, ecx, edx;
 	u8 *temp;
@@ -440,13 +443,11 @@
 	phy_dev_entry->first_cpu = cpu;
 	phy_dev_entry->tj_max = tj_max;
 	phy_dev_entry->ref_cnt = 1;
-	snprintf(buffer, sizeof(buffer), "pkg-temp-%d\n",
-					phy_dev_entry->phys_proc_id);
-	phy_dev_entry->tzone = thermal_zone_device_register(buffer,
+	phy_dev_entry->tzone = thermal_zone_device_register("x86_pkg_temp",
 			thres_count,
 			(thres_count == MAX_NUMBER_OF_TRIPS) ?
 				0x03 : 0x01,
-			phy_dev_entry, &tzone_ops, NULL, 0, 0);
+			phy_dev_entry, &tzone_ops, &pkg_temp_tz_params, 0, 0);
 	if (IS_ERR(phy_dev_entry->tzone)) {
 		err = PTR_ERR(phy_dev_entry->tzone);
 		goto err_ret_free;
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 8d72f0c..062967c 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -717,6 +717,10 @@
 			result = -ENOMEM;
 			goto err;
 		}
+
+		if (dev->quirks & USB_QUIRK_DELAY_INIT)
+			msleep(100);
+
 		result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno,
 		    bigbuffer, length);
 		if (result < 0) {
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8f37063..739ee8e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -47,6 +47,10 @@
 	/* Microsoft LifeCam-VX700 v2.0 */
 	{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech HD Pro Webcams C920 and C930e */
+	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Logitech Quickcam Fusion */
 	{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
 
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 4711427..81cda09 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -685,8 +685,15 @@
 	struct ehci_hcd		*ehci = hcd_to_ehci (hcd);
 	u32			status, masked_status, pcd_status = 0, cmd;
 	int			bh;
+	unsigned long		flags;
 
-	spin_lock (&ehci->lock);
+	/*
+	 * For threadirqs option we use spin_lock_irqsave() variant to prevent
+	 * deadlock with ehci hrtimer callback, because hrtimer callbacks run
+	 * in interrupt context even when threadirqs is specified. We can go
+	 * back to spin_lock() variant when hrtimer callbacks become threaded.
+	 */
+	spin_lock_irqsave(&ehci->lock, flags);
 
 	status = ehci_readl(ehci, &ehci->regs->status);
 
@@ -704,7 +711,7 @@
 
 	/* Shared IRQ? */
 	if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
-		spin_unlock(&ehci->lock);
+		spin_unlock_irqrestore(&ehci->lock, flags);
 		return IRQ_NONE;
 	}
 
@@ -815,7 +822,7 @@
 
 	if (bh)
 		ehci_work (ehci);
-	spin_unlock (&ehci->lock);
+	spin_unlock_irqrestore(&ehci->lock, flags);
 	if (pcd_status)
 		usb_hcd_poll_rh_status(hcd);
 	return IRQ_HANDLED;
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6fe577d..924a6cc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4733,6 +4733,9 @@
 	/* Accept arbitrarily long scatter-gather lists */
 	hcd->self.sg_tablesize = ~0;
 
+	/* support to build packet from discontinuous buffers */
+	hcd->self.no_sg_constraint = 1;
+
 	/* XHCI controllers don't stop the ep queue on short packets :| */
 	hcd->self.no_stop_on_short = 1;
 
@@ -4757,14 +4760,6 @@
 		/* xHCI private pointer was set in xhci_pci_probe for the second
 		 * registered roothub.
 		 */
-		xhci = hcd_to_xhci(hcd);
-		/*
-		 * Support arbitrarily aligned sg-list entries on hosts without
-		 * TD fragment rules (which are currently unsupported).
-		 */
-		if (xhci->hci_version < 0x100)
-			hcd->self.no_sg_constraint = 1;
-
 		return 0;
 	}
 
@@ -4793,9 +4788,6 @@
 	if (xhci->hci_version > 0x96)
 		xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
 
-	if (xhci->hci_version < 0x100)
-		hcd->self.no_sg_constraint = 1;
-
 	/* Make sure the HC is halted. */
 	retval = xhci_halt(xhci);
 	if (retval)
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ee1f00f..44ab129 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -907,6 +907,8 @@
 	/* Crucible Devices */
 	{ USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) },
+	/* Cressi Devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 1e2d369..e599fbf 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1320,3 +1320,9 @@
  * Manufacturer: Smart GSM Team
  */
 #define FTDI_Z3X_PID		0x0011
+
+/*
+ * Product: Cressi PC Interface
+ * Manufacturer: Cressi
+ */
+#define FTDI_CRESSI_PID		0x87d0
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 4fb7a8f..54af4e9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -186,12 +186,12 @@
 	if (pfn_valid(pfn)) {
 		bool reserved;
 		struct page *tail = pfn_to_page(pfn);
-		struct page *head = compound_trans_head(tail);
+		struct page *head = compound_head(tail);
 		reserved = !!(PageReserved(head));
 		if (head != tail) {
 			/*
 			 * "head" is not a dangling pointer
-			 * (compound_trans_head takes care of that)
+			 * (compound_head takes care of that)
 			 * but the hugepage may have been split
 			 * from under us (and we may not hold a
 			 * reference count on the head page so it can
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 0a025b8..e48d4a6 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1001,6 +1001,12 @@
 			break;
 		}
 
+		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
+		if (unlikely(v_req.lun[0] != 1)) {
+			vhost_scsi_send_bad_target(vs, vq, head, out);
+			continue;
+		}
+
 		/* Extract the tpgt */
 		target = v_req.lun[1];
 		tpg = ACCESS_ONCE(vs_tpg[target]);
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 0129b78..4f70f38 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -458,11 +458,10 @@
 	struct blk_integrity_exchg bix;
 	struct bio_vec *bv;
 	sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
-	unsigned int sectors, total, ret;
+	unsigned int sectors, ret = 0;
 	void *prot_buf = bio->bi_integrity->bip_buf;
 	int i;
 
-	ret = total = 0;
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
 
@@ -484,8 +483,6 @@
 		sectors = bv->bv_len / bi->sector_size;
 		sector += sectors;
 		prot_buf += sectors * bi->tuple_size;
-		total += sectors * bi->tuple_size;
-		BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
 
 		kunmap_atomic(kaddr);
 	}
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index cf32f03..c0f3718 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -513,7 +513,7 @@
 static inline unsigned int
 get_rfc1002_length(void *buf)
 {
-	return be32_to_cpu(*((__be32 *)buf));
+	return be32_to_cpu(*((__be32 *)buf)) & 0xffffff;
 }
 
 static inline void
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 53c1507..834fce7 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2579,31 +2579,19 @@
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
 	ssize_t rc = -EACCES;
+	loff_t lock_pos = pos;
 
-	BUG_ON(iocb->ki_pos != pos);
-
+	if (file->f_flags & O_APPEND)
+		lock_pos = i_size_read(inode);
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
 	 * with a brlock that prevents writing.
 	 */
 	down_read(&cinode->lock_sem);
-	if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs),
+	if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs),
 				     server->vals->exclusive_lock_type, NULL,
-				     CIFS_WRITE_OP)) {
-		mutex_lock(&inode->i_mutex);
-		rc = __generic_file_aio_write(iocb, iov, nr_segs,
-					       &iocb->ki_pos);
-		mutex_unlock(&inode->i_mutex);
-	}
-
-	if (rc > 0) {
-		ssize_t err;
-
-		err = generic_write_sync(file, iocb->ki_pos - rc, rc);
-		if (err < 0)
-			rc = err;
-	}
-
+				     CIFS_WRITE_OP))
+		rc = generic_file_aio_write(iocb, iov, nr_segs, pos);
 	up_read(&cinode->lock_sem);
 	return rc;
 }
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index b375709..18cd565 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -270,6 +270,26 @@
 		iov->iov_len = rqst->rq_pagesz;
 }
 
+static unsigned long
+rqst_len(struct smb_rqst *rqst)
+{
+	unsigned int i;
+	struct kvec *iov = rqst->rq_iov;
+	unsigned long buflen = 0;
+
+	/* total up iov array first */
+	for (i = 0; i < rqst->rq_nvec; i++)
+		buflen += iov[i].iov_len;
+
+	/* add in the page array if there is one */
+	if (rqst->rq_npages) {
+		buflen += rqst->rq_pagesz * (rqst->rq_npages - 1);
+		buflen += rqst->rq_tailsz;
+	}
+
+	return buflen;
+}
+
 static int
 smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
@@ -277,6 +297,7 @@
 	struct kvec *iov = rqst->rq_iov;
 	int n_vec = rqst->rq_nvec;
 	unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
+	unsigned long send_length;
 	unsigned int i;
 	size_t total_len = 0, sent;
 	struct socket *ssocket = server->ssocket;
@@ -285,6 +306,14 @@
 	if (ssocket == NULL)
 		return -ENOTSOCK;
 
+	/* sanity check send length */
+	send_length = rqst_len(rqst);
+	if (send_length != smb_buf_length + 4) {
+		WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n",
+			send_length, smb_buf_length);
+		return -EIO;
+	}
+
 	cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
 	dump_smb(iov[0].iov_base, iov[0].iov_len);
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 265e0ce..66dc62c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3112,6 +3112,7 @@
 		end = ERR_PTR(-ENAMETOOLONG);
 	return end;
 }
+EXPORT_SYMBOL(simple_dname);
 
 /*
  * Write full pathname from the root of the filesystem into the buffer.
diff --git a/fs/file.c b/fs/file.c
index db25c2b..60a45e9 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -683,35 +683,65 @@
  * The fput_needed flag returned by fget_light should be passed to the
  * corresponding fput_light.
  */
-struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed)
+static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
 
-	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = __fcheck_files(files, fd);
-		if (file && (file->f_mode & mask))
-			file = NULL;
+		if (!file || unlikely(file->f_mode & mask))
+			return 0;
+		return (unsigned long)file;
 	} else {
 		file = __fget(fd, mask);
-		if (file)
-			*fput_needed = 1;
+		if (!file)
+			return 0;
+		return FDPUT_FPUT | (unsigned long)file;
 	}
-
-	return file;
 }
-struct file *fget_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget(unsigned int fd)
 {
-	return __fget_light(fd, FMODE_PATH, fput_needed);
+	return __fget_light(fd, FMODE_PATH);
 }
-EXPORT_SYMBOL(fget_light);
+EXPORT_SYMBOL(__fdget);
 
-struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget_raw(unsigned int fd)
 {
-	return __fget_light(fd, 0, fput_needed);
+	return __fget_light(fd, 0);
 }
 
+unsigned long __fdget_pos(unsigned int fd)
+{
+	struct files_struct *files = current->files;
+	struct file *file;
+	unsigned long v;
+
+	if (atomic_read(&files->count) == 1) {
+		file = __fcheck_files(files, fd);
+		v = 0;
+	} else {
+		file = __fget(fd, 0);
+		v = FDPUT_FPUT;
+	}
+	if (!file)
+		return 0;
+
+	if (file->f_mode & FMODE_ATOMIC_POS) {
+		if (file_count(file) > 1) {
+			v |= FDPUT_POS_UNLOCK;
+			mutex_lock(&file->f_pos_lock);
+		}
+	}
+	return v | (unsigned long)file;
+}
+
+/*
+ * We only lock f_pos if we have threads or if the file might be
+ * shared with another process. In both cases we'll have an elevated
+ * file count (done either by fdget() or by fork()).
+ */
+
 void set_close_on_exec(unsigned int fd, int flag)
 {
 	struct files_struct *files = current->files;
diff --git a/fs/file_table.c b/fs/file_table.c
index 5fff903..5b24008 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -135,6 +135,7 @@
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
+	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
 	return f;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e0259a1..d754e3c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	/*
-	 * Write only inodes dirtied before this time. Don't forget to set
-	 * older_than_this_is_set when you set this.
-	 */
-	unsigned long older_than_this;
+	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
-	unsigned int older_than_this_is_set:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
@@ -252,10 +247,10 @@
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	WARN_ON_ONCE(!work->older_than_this_is_set);
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (inode_dirtied_after(inode, work->older_than_this))
+		if (work->older_than_this &&
+		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
@@ -742,8 +737,6 @@
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
 		.reason		= reason,
-		.older_than_this = jiffies,
-		.older_than_this_is_set = 1,
 	};
 
 	spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
+	unsigned long oldest_jif;
 	struct inode *inode;
 	long progress;
 
-	if (!work->older_than_this_is_set) {
-		work->older_than_this = jiffies;
-		work->older_than_this_is_set = 1;
-	}
+	oldest_jif = jiffies;
+	work->older_than_this = &oldest_jif;
 
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -842,10 +834,10 @@
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			work->older_than_this = jiffies -
+			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			work->older_than_this = jiffies;
+			oldest_jif = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
- * @sb:			the superblock
- * @older_than_this:	timestamp
+ * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
  */
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
 		.nr_pages	= LONG_MAX,
-		.older_than_this = older_than_this,
-		.older_than_this_is_set = 1,
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 968ce41..32602c6 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -103,6 +103,8 @@
 		folder = &entry->folder;
 		memset(folder, 0, sizeof(*folder));
 		folder->type = cpu_to_be16(HFSPLUS_FOLDER);
+		if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags))
+			folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT);
 		folder->id = cpu_to_be32(inode->i_ino);
 		HFSPLUS_I(inode)->create_date =
 			folder->create_date =
@@ -203,6 +205,36 @@
 	return hfs_brec_find(fd, hfs_find_rec_by_key);
 }
 
+static void hfsplus_subfolders_inc(struct inode *dir)
+{
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+	if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+		/*
+		 * Increment subfolder count. Note, the value is only meaningful
+		 * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+		 */
+		HFSPLUS_I(dir)->subfolders++;
+	}
+}
+
+static void hfsplus_subfolders_dec(struct inode *dir)
+{
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+	if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+		/*
+		 * Decrement subfolder count. Note, the value is only meaningful
+		 * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+		 *
+		 * Check for zero. Some subfolders may have been created
+		 * by an implementation ignorant of this counter.
+		 */
+		if (HFSPLUS_I(dir)->subfolders)
+			HFSPLUS_I(dir)->subfolders--;
+	}
+}
+
 int hfsplus_create_cat(u32 cnid, struct inode *dir,
 		struct qstr *str, struct inode *inode)
 {
@@ -247,6 +279,8 @@
 		goto err1;
 
 	dir->i_size++;
+	if (S_ISDIR(inode->i_mode))
+		hfsplus_subfolders_inc(dir);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
 
@@ -336,6 +370,8 @@
 		goto out;
 
 	dir->i_size--;
+	if (type == HFSPLUS_FOLDER)
+		hfsplus_subfolders_dec(dir);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
 
@@ -380,6 +416,7 @@
 
 	hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset,
 				src_fd.entrylength);
+	type = be16_to_cpu(entry.type);
 
 	/* create new dir entry with the data from the old entry */
 	hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
@@ -394,6 +431,8 @@
 	if (err)
 		goto out;
 	dst_dir->i_size++;
+	if (type == HFSPLUS_FOLDER)
+		hfsplus_subfolders_inc(dst_dir);
 	dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* finally remove the old entry */
@@ -405,6 +444,8 @@
 	if (err)
 		goto out;
 	src_dir->i_size--;
+	if (type == HFSPLUS_FOLDER)
+		hfsplus_subfolders_dec(src_dir);
 	src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* remove old thread entry */
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 08846425b..62d571e 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -242,6 +242,7 @@
 	 */
 	sector_t fs_blocks;
 	u8 userflags;		/* BSD user file flags */
+	u32 subfolders;		/* Subfolder count (HFSX only) */
 	struct list_head open_dir_list;
 	loff_t phys_size;
 
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 8ffb3a8..5a12682 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -261,7 +261,7 @@
 	struct DInfo user_info;
 	struct DXInfo finder_info;
 	__be32 text_encoding;
-	u32 reserved;
+	__be32 subfolders;	/* Subfolder count in HFSX. Reserved in HFS+. */
 } __packed;
 
 /* HFS file info (stolen from hfs.h) */
@@ -301,11 +301,13 @@
 	struct hfsplus_fork_raw rsrc_fork;
 } __packed;
 
-/* File attribute bits */
+/* File and folder flag bits */
 #define HFSPLUS_FILE_LOCKED		0x0001
 #define HFSPLUS_FILE_THREAD_EXISTS	0x0002
 #define HFSPLUS_XATTR_EXISTS		0x0004
 #define HFSPLUS_ACL_EXISTS		0x0008
+#define HFSPLUS_HAS_FOLDER_COUNT	0x0010	/* Folder has subfolder count
+						 * (HFSX only) */
 
 /* HFS+ catalog thread (part of a cat_entry) */
 struct hfsplus_cat_thread {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index fa929f3..a4f45bd 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -375,6 +375,7 @@
 	hip->extent_state = 0;
 	hip->flags = 0;
 	hip->userflags = 0;
+	hip->subfolders = 0;
 	memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
 	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
 	hip->alloc_blocks = 0;
@@ -494,6 +495,10 @@
 		inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
 		HFSPLUS_I(inode)->create_date = folder->create_date;
 		HFSPLUS_I(inode)->fs_blocks = 0;
+		if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+			HFSPLUS_I(inode)->subfolders =
+				be32_to_cpu(folder->subfolders);
+		}
 		inode->i_op = &hfsplus_dir_inode_operations;
 		inode->i_fop = &hfsplus_dir_operations;
 	} else if (type == HFSPLUS_FILE) {
@@ -566,6 +571,10 @@
 		folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
 		folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
 		folder->valence = cpu_to_be32(inode->i_size - 2);
+		if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+			folder->subfolders =
+				cpu_to_be32(HFSPLUS_I(inode)->subfolders);
+		}
 		hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
 					 sizeof(struct hfsplus_cat_folder));
 	} else if (HFSPLUS_IS_RSRC(inode)) {
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 968eab5..68537e8 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -75,7 +75,7 @@
 	int token;
 
 	if (!input)
-		return 0;
+		return 1;
 
 	while ((p = strsep(&input, ",")) != NULL) {
 		if (!*p)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce89..0f4152d 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -94,6 +94,7 @@
  * @fs_type: file_system_type of the fs being mounted
  * @flags: mount flags specified for the mount
  * @root: kernfs_root of the hierarchy being mounted
+ * @new_sb_created: tell the caller if we allocated a new superblock
  * @ns: optional namespace tag of the mount
  *
  * This is to be called from each kernfs user's file_system_type->mount()
@@ -104,7 +105,8 @@
  * The return value can be passed to the vfs layer verbatim.
  */
 struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-			       struct kernfs_root *root, const void *ns)
+			       struct kernfs_root *root, bool *new_sb_created,
+			       const void *ns)
 {
 	struct super_block *sb;
 	struct kernfs_super_info *info;
@@ -122,6 +124,10 @@
 		kfree(info);
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
+
+	if (new_sb_created)
+		*new_sb_created = !sb->s_root;
+
 	if (!sb->s_root) {
 		error = kernfs_fill_super(sb);
 		if (error) {
diff --git a/fs/namei.c b/fs/namei.c
index 385f781..2f730ef 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1884,7 +1884,7 @@
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			if (f.need_put)
+			if (f.flags & FDPUT_FPUT)
 				*fp = f.file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			rcu_read_lock();
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ef792f2..5d8ccec 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -659,16 +659,19 @@
 
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation == NULL)
+		goto out_enoent;
 
-	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
-		rcu_read_unlock();
-		return -ENOENT;
-	}
+	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+		goto out_enoent;
 	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
 
 	nfs_delegation_run_state_manager(clp);
 	return 0;
+out_enoent:
+	rcu_read_unlock();
+	return -ENOENT;
 }
 
 static struct inode *
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 12c8132..b9a35c0 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -324,8 +324,9 @@
 			&rdata->res.seq_res,
 			task))
 		return;
-	nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
-			rdata->args.lock_context, FMODE_READ);
+	if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+			rdata->args.lock_context, FMODE_READ) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
 }
 
 static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -435,8 +436,9 @@
 			&wdata->res.seq_res,
 			task))
 		return;
-	nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
-			wdata->args.lock_context, FMODE_WRITE);
+	if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+			wdata->args.lock_context, FMODE_WRITE) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
 }
 
 static void filelayout_write_call_done(struct rpc_task *task, void *data)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2da6a69..450bfed 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2398,13 +2398,16 @@
 
 	if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
 		/* Use that stateid */
-	} else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
+	} else if (truncate && state != NULL) {
 		struct nfs_lockowner lockowner = {
 			.l_owner = current->files,
 			.l_pid = current->tgid,
 		};
-		nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
-				&lockowner);
+		if (!nfs4_valid_open_stateid(state))
+			return -EBADF;
+		if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+				&lockowner) == -EIO)
+			return -EBADF;
 	} else
 		nfs4_stateid_copy(&arg.stateid, &zero_stateid);
 
@@ -4011,8 +4014,9 @@
 {
 	nfs4_stateid current_stateid;
 
-	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
-		return false;
+	/* If the current stateid represents a lost lock, then exit */
+	if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+		return true;
 	return nfs4_stateid_match(stateid, &current_stateid);
 }
 
@@ -5828,8 +5832,7 @@
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server;
 	struct nfs_release_lockowner_args args;
-	struct nfs4_sequence_args seq_args;
-	struct nfs4_sequence_res seq_res;
+	struct nfs_release_lockowner_res res;
 	unsigned long timestamp;
 };
 
@@ -5837,7 +5840,7 @@
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	nfs40_setup_sequence(data->server,
-				&data->seq_args, &data->seq_res, task);
+				&data->args.seq_args, &data->res.seq_res, task);
 	data->timestamp = jiffies;
 }
 
@@ -5846,7 +5849,7 @@
 	struct nfs_release_lockowner_data *data = calldata;
 	struct nfs_server *server = data->server;
 
-	nfs40_sequence_done(task, &data->seq_res);
+	nfs40_sequence_done(task, &data->res.seq_res);
 
 	switch (task->tk_status) {
 	case 0:
@@ -5887,7 +5890,6 @@
 	data = kmalloc(sizeof(*data), GFP_NOFS);
 	if (!data)
 		return -ENOMEM;
-	nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
 	data->lsp = lsp;
 	data->server = server;
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5895,6 +5897,8 @@
 	data->args.lock_owner.s_dev = server->s_dev;
 
 	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
+	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
 	rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
 	return 0;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e1a4721..0deb321 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -974,9 +974,6 @@
 	else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
 		nfs4_stateid_copy(dst, &lsp->ls_stateid);
 		ret = 0;
-		smp_rmb();
-		if (!list_empty(&lsp->ls_seqid.list))
-			ret = -EWOULDBLOCK;
 	}
 	spin_unlock(&state->state_lock);
 	nfs4_put_lock_state(lsp);
@@ -984,10 +981,9 @@
 	return ret;
 }
 
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 {
 	const nfs4_stateid *src;
-	int ret;
 	int seq;
 
 	do {
@@ -996,12 +992,7 @@
 		if (test_bit(NFS_OPEN_STATE, &state->flags))
 			src = &state->open_stateid;
 		nfs4_stateid_copy(dst, src);
-		ret = 0;
-		smp_rmb();
-		if (!list_empty(&state->owner->so_seqid.list))
-			ret = -EWOULDBLOCK;
 	} while (read_seqretry(&state->seqlock, seq));
-	return ret;
 }
 
 /*
@@ -1026,7 +1017,8 @@
 		 * choose to use.
 		 */
 		goto out;
-	ret = nfs4_copy_open_stateid(dst, state);
+	nfs4_copy_open_stateid(dst, state);
+	ret = 0;
 out:
 	if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
 		dst->seqid = 0;
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 0b9ff43..abc8cbc 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -86,7 +86,7 @@
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name)
+				const unsigned char *file_name, u32 cookie)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 0e792f5..dc638f7 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -147,7 +147,7 @@
 				 struct fsnotify_mark *inode_mark,
 				 struct fsnotify_mark *fanotify_mark,
 				 u32 mask, void *data, int data_type,
-				 const unsigned char *file_name)
+				 const unsigned char *file_name, u32 cookie)
 {
 	int ret = 0;
 	struct fanotify_event_info *event;
@@ -192,10 +192,12 @@
 
 	ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
 	if (ret) {
-		BUG_ON(mask & FAN_ALL_PERM_EVENTS);
+		/* Permission events shouldn't be merged */
+		BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);
-		ret = 0;
+
+		return 0;
 	}
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b6175fa..287a22c 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -698,6 +698,7 @@
 	struct fsnotify_group *group;
 	int f_flags, fd;
 	struct user_struct *user;
+	struct fanotify_event_info *oevent;
 
 	pr_debug("%s: flags=%d event_f_flags=%d\n",
 		__func__, flags, event_f_flags);
@@ -730,8 +731,20 @@
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
 
+	oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fd = -ENOMEM;
+		goto out_destroy_group;
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->tgid = get_pid(task_tgid(current));
+	oevent->path.mnt = NULL;
+	oevent->path.dentry = NULL;
+
 	group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	oevent->response = 0;
 	mutex_init(&group->fanotify_data.access_mutex);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 1d4e1ea..9d3e9c5 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -179,7 +179,7 @@
 
 	return group->ops->handle_event(group, to_tell, inode_mark,
 					vfsmount_mark, mask, data, data_is,
-					file_name);
+					file_name, cookie);
 }
 
 /*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ee674fe..ad19959 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -55,6 +55,13 @@
 	/* clear the notification queue of all events */
 	fsnotify_flush_notify(group);
 
+	/*
+	 * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+	 * that deliberately ignores overflow events.
+	 */
+	if (group->overflow_event)
+		group->ops->free_event(group->overflow_event);
+
 	fsnotify_put_group(group);
 }
 
@@ -99,7 +106,6 @@
 	INIT_LIST_HEAD(&group->marks_list);
 
 	group->ops = ops;
-	fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
 
 	return group;
 }
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 485eef3..ed855ef 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,6 @@
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name);
+				const unsigned char *file_name, u32 cookie);
 
 extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d5ee563..43ab1e1 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -67,7 +67,7 @@
 			 struct fsnotify_mark *inode_mark,
 			 struct fsnotify_mark *vfsmount_mark,
 			 u32 mask, void *data, int data_type,
-			 const unsigned char *file_name)
+			 const unsigned char *file_name, u32 cookie)
 {
 	struct inotify_inode_mark *i_mark;
 	struct inotify_event_info *event;
@@ -103,6 +103,7 @@
 	fsn_event = &event->fse;
 	fsnotify_init_event(fsn_event, inode, mask);
 	event->wd = i_mark->wd;
+	event->sync_cookie = cookie;
 	event->name_len = len;
 	if (len)
 		strcpy(event->name, file_name);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 497395c..78a2ca3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -495,7 +495,7 @@
 
 	/* Queue ignore event for the watch */
 	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
-			     NULL, FSNOTIFY_EVENT_NONE, NULL);
+			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 	/* remove this mark from the idr */
@@ -633,11 +633,23 @@
 static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 {
 	struct fsnotify_group *group;
+	struct inotify_event_info *oevent;
 
 	group = fsnotify_alloc_group(&inotify_fsnotify_ops);
 	if (IS_ERR(group))
 		return group;
 
+	oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fsnotify_destroy_group(group);
+		return ERR_PTR(-ENOMEM);
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->wd = -1;
+	oevent->sync_cookie = 0;
+	oevent->name_len = 0;
+
 	group->max_events = max_events;
 
 	spin_lock_init(&group->inotify_data.idr_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 18b3c44..1e58402 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -80,7 +80,8 @@
 /*
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event.
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
  */
 int fsnotify_add_notify_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
@@ -95,10 +96,14 @@
 	mutex_lock(&group->notification_mutex);
 
 	if (group->q_len >= group->max_events) {
+		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
-		if (list_empty(&group->overflow_event.list))
-			event = &group->overflow_event;
-		ret = 1;
+		if (!list_empty(&group->overflow_event->list)) {
+			mutex_unlock(&group->notification_mutex);
+			return ret;
+		}
+		event = group->overflow_event;
+		goto queue;
 	}
 
 	if (!list_empty(list) && merge) {
@@ -109,6 +114,7 @@
 		}
 	}
 
+queue:
 	group->q_len++;
 	list_add_tail(&event->list, list);
 	mutex_unlock(&group->notification_mutex);
@@ -132,7 +138,11 @@
 
 	event = list_first_entry(&group->notification_list,
 				 struct fsnotify_event, list);
-	list_del(&event->list);
+	/*
+	 * We need to init list head for the case of overflow event so that
+	 * check in fsnotify_add_notify_events() works
+	 */
+	list_del_init(&event->list);
 	group->q_len--;
 
 	return event;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8450262bc..51632c4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2393,8 +2393,8 @@
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
 	    ((file->f_flags & O_DIRECT) && !direct_io)) {
-		ret = filemap_fdatawrite_range(file->f_mapping, pos,
-					       pos + count - 1);
+		ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+					       *ppos + count - 1);
 		if (ret < 0)
 			written = ret;
 
@@ -2407,8 +2407,8 @@
 		}
 
 		if (!ret)
-			ret = filemap_fdatawait_range(file->f_mapping, pos,
-						      pos + count - 1);
+			ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+						      *ppos + count - 1);
 	}
 
 	/*
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa5061..d7b5108 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@
 	 */
 	if (status < 0)
 		mlog_errno(status);
+	/*
+	 * Clear dq_off so that we search for the structure in quota file next
+	 * time we acquire it. The structure might be deleted and reallocated
+	 * elsewhere by another node while our dquot structure is on freelist.
+	 */
+	dquot->dq_off = 0;
 	clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_trans:
 	ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@
 	status = ocfs2_lock_global_qf(info, 1);
 	if (status < 0)
 		goto out;
-	if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
-		status = ocfs2_qinfo_lock(info, 0);
-		if (status < 0)
-			goto out_dq;
-		status = qtree_read_dquot(&info->dqi_gi, dquot);
-		ocfs2_qinfo_unlock(info, 0);
-		if (status < 0)
-			goto out_dq;
-	}
-	set_bit(DQ_READ_B, &dquot->dq_flags);
+	status = ocfs2_qinfo_lock(info, 0);
+	if (status < 0)
+		goto out_dq;
+	/*
+	 * We always want to read dquot structure from disk because we don't
+	 * know what happened with it while it was on freelist.
+	 */
+	status = qtree_read_dquot(&info->dqi_gi, dquot);
+	ocfs2_qinfo_unlock(info, 0);
+	if (status < 0)
+		goto out_dq;
 
 	OCFS2_DQUOT(dquot)->dq_use_count++;
 	OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344b..2001862 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@
 	ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
 
 out:
-	/* Clear the read bit so that next time someone uses this
-	 * dquot he reads fresh info from disk and allocates local
-	 * dquot structure */
-	clear_bit(DQ_READ_B, &dquot->dq_flags);
 	return status;
 }
 
diff --git a/fs/open.c b/fs/open.c
index 4b3e1ed..b9ed8b2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -705,6 +705,10 @@
 		return 0;
 	}
 
+	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+	if (S_ISREG(inode->i_mode))
+		f->f_mode |= FMODE_ATOMIC_POS;
+
 	f->f_op = fops_get(inode->i_fop);
 	if (unlikely(WARN_ON(!f->f_op))) {
 		error = -ENODEV;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5150706..b976062 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1824,6 +1824,7 @@
 	if (rc)
 		goto out_mmput;
 
+	rc = -ENOENT;
 	down_read(&mm->mmap_sem);
 	vma = find_exact_vma(mm, vm_start, vm_end);
 	if (vma && vma->vm_file) {
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 02174a6..e647c55 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,9 +121,8 @@
 	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
 	 * to make sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) &&
-		 (PageLRU(compound_trans_head(page)) ||
-		  PageAnon(compound_trans_head(page))))
+	else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
+					     PageAnon(compound_head(page))))
 		u |= 1 << KPF_THP;
 
 	/*
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 831d49a..cfc8dcc 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@
 		dqstats_inc(DQST_LOOKUPS);
 		dqput(old_dquot);
 		old_dquot = dquot;
-		ret = fn(dquot, priv);
-		if (ret < 0)
-			goto out;
+		/*
+		 * ->release_dquot() can be racing with us. Our reference
+		 * protects us from new calls to it so just wait for any
+		 * outstanding call and recheck the DQ_ACTIVE_B after that.
+		 */
+		wait_on_dquot(dquot);
+		if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+			ret = fn(dquot, priv);
+			if (ret < 0)
+				goto out;
+		}
 		spin_lock(&dq_list_lock);
 		/* We are safe to continue now because our dquot could not
 		 * be moved out of the inuse list while we hold the reference */
diff --git a/fs/read_write.c b/fs/read_write.c
index edc5746..54e19b9 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -264,10 +264,22 @@
 }
 EXPORT_SYMBOL(vfs_llseek);
 
+static inline struct fd fdget_pos(int fd)
+{
+	return __to_fd(__fdget_pos(fd));
+}
+
+static inline void fdput_pos(struct fd f)
+{
+	if (f.flags & FDPUT_POS_UNLOCK)
+		mutex_unlock(&f.file->f_pos_lock);
+	fdput(f);
+}
+
 SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
 {
 	off_t retval;
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	if (!f.file)
 		return -EBADF;
 
@@ -278,7 +290,7 @@
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
 	}
-	fdput(f);
+	fdput_pos(f);
 	return retval;
 }
 
@@ -498,7 +510,7 @@
 
 SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -506,7 +518,7 @@
 		ret = vfs_read(f.file, buf, count, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 	return ret;
 }
@@ -514,7 +526,7 @@
 SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 		size_t, count)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -522,7 +534,7 @@
 		ret = vfs_write(f.file, buf, count, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	return ret;
@@ -797,7 +809,7 @@
 SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -805,7 +817,7 @@
 		ret = vfs_readv(f.file, vec, vlen, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	if (ret > 0)
@@ -817,7 +829,7 @@
 SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -825,7 +837,7 @@
 		ret = vfs_writev(f.file, vec, vlen, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	if (ret > 0)
@@ -968,7 +980,7 @@
 		const struct compat_iovec __user *,vec,
 		compat_ulong_t, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret;
 	loff_t pos;
 
@@ -978,7 +990,7 @@
 	ret = compat_readv(f.file, vec, vlen, &pos);
 	if (ret >= 0)
 		f.file->f_pos = pos;
-	fdput(f);
+	fdput_pos(f);
 	return ret;
 }
 
@@ -1035,7 +1047,7 @@
 		const struct compat_iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret;
 	loff_t pos;
 
@@ -1045,7 +1057,7 @@
 	ret = compat_writev(f.file, vec, vlen, &pos);
 	if (ret >= 0)
 		f.file->f_pos = pos;
-	fdput(f);
+	fdput_pos(f);
 	return ret;
 }
 
diff --git a/fs/sync.c b/fs/sync.c
index e8ba024..b28d1dd 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,11 +27,10 @@
  * wait == 1 case since in that case write_inode() functions do
  * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static int __sync_filesystem(struct super_block *sb, int wait,
-			     unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
 {
 	if (wait)
-		sync_inodes_sb(sb, start);
+		sync_inodes_sb(sb);
 	else
 		writeback_inodes_sb(sb, WB_REASON_SYNC);
 
@@ -48,7 +47,6 @@
 int sync_filesystem(struct super_block *sb)
 {
 	int ret;
-	unsigned long start = jiffies;
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
-	ret = __sync_filesystem(sb, 0, start);
+	ret = __sync_filesystem(sb, 0);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1, start);
+	return __sync_filesystem(sb, 1);
 }
 EXPORT_SYMBOL_GPL(sync_filesystem);
 
 static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
 	if (!(sb->s_flags & MS_RDONLY))
-		sync_inodes_sb(sb, *((unsigned long *)arg));
+		sync_inodes_sb(sb);
 }
 
 static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@
 SYSCALL_DEFINE0(sync)
 {
 	int nowait = 0, wait = 1;
-	unsigned long start = jiffies;
 
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
-	iterate_supers(sync_inodes_one_sb, &start);
+	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &wait);
 	iterate_bdevs(fdatawrite_one_bdev, NULL);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230..3eaf5c6 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@
 {
 	struct dentry *root;
 	void *ns;
+	bool new_sb;
 
 	if (!(flags & MS_KERNMOUNT)) {
 		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@
 	}
 
 	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
-	root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
-	if (IS_ERR(root))
+	root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns);
+	if (IS_ERR(root) || !new_sb)
 		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
 	return root;
 }
diff --git a/fs/udf/file.c b/fs/udf/file.c
index c02a27a..1037637 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -144,6 +144,7 @@
 	size_t count = iocb->ki_nbytes;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
+	mutex_lock(&inode->i_mutex);
 	down_write(&iinfo->i_data_sem);
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 		if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@
 						pos + count)) {
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
+				mutex_unlock(&inode->i_mutex);
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
 				return err;
 			}
@@ -169,9 +171,17 @@
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
-	if (retval > 0)
+	retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	mutex_unlock(&inode->i_mutex);
+
+	if (retval > 0) {
+		ssize_t err;
+
 		mark_inode_dirty(inode);
+		err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+		if (err < 0)
+			retval = err;
+	}
 
 	return retval;
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 062b792..982ce05 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -265,6 +265,7 @@
 		.nr_to_write = 1,
 	};
 
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
 	if (!iinfo->i_lenAlloc) {
 		if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f317488..d971f49 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -913,7 +913,7 @@
 	struct super_block	*sb = mp->m_super;
 
 	if (down_read_trylock(&sb->s_umount)) {
-		sync_inodes_sb(sb, jiffies);
+		sync_inodes_sb(sb);
 		up_read(&sb->s_umount);
 	}
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 04a7f31..daac00a 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -43,6 +43,7 @@
 #include <asm/current.h>
 #endif				/* __alpha__ */
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -1008,10 +1009,12 @@
 	struct list_head legacy_dev_list;
 };
 
-#define DRM_MINOR_UNASSIGNED 0
-#define DRM_MINOR_LEGACY 1
-#define DRM_MINOR_CONTROL 2
-#define DRM_MINOR_RENDER 3
+enum drm_minor_type {
+	DRM_MINOR_LEGACY,
+	DRM_MINOR_CONTROL,
+	DRM_MINOR_RENDER,
+	DRM_MINOR_CNT,
+};
 
 /**
  * Info file list entry. This structure represents a debugfs or proc file to
@@ -1040,7 +1043,6 @@
 struct drm_minor {
 	int index;			/**< Minor device number */
 	int type;                       /**< Control or render */
-	dev_t device;			/**< Device number for mknod */
 	struct device *kdev;		/**< Linux device */
 	struct drm_device *dev;
 
@@ -1054,21 +1056,6 @@
 	struct drm_mode_group mode_group;
 };
 
-/* mode specified on the command line */
-struct drm_cmdline_mode {
-	bool specified;
-	bool refresh_specified;
-	bool bpp_specified;
-	int xres, yres;
-	int bpp;
-	int refresh;
-	bool rb;
-	bool interlace;
-	bool cvt;
-	bool margins;
-	enum drm_connector_force force;
-};
-
 
 struct drm_pending_vblank_event {
 	struct drm_pending_event base;
@@ -1098,6 +1085,19 @@
 	char *devname;			/**< For /proc/interrupts */
 	int if_version;			/**< Highest interface version set */
 
+	/** \name Lifetime Management */
+	/*@{ */
+	struct kref ref;		/**< Object ref-count */
+	struct device *dev;		/**< Device structure of bus-device */
+	struct drm_driver *driver;	/**< DRM driver managing the device */
+	void *dev_private;		/**< DRM driver private data */
+	struct drm_minor *control;		/**< Control node */
+	struct drm_minor *primary;		/**< Primary node */
+	struct drm_minor *render;		/**< Render node */
+	atomic_t unplugged;			/**< Flag whether dev is dead */
+	struct inode *anon_inode;		/**< inode for private address-space */
+	/*@} */
+
 	/** \name Locks */
 	/*@{ */
 	spinlock_t count_lock;		/**< For inuse, drm_device::open_count, drm_device::buf_use */
@@ -1171,7 +1171,6 @@
 
 	struct drm_agp_head *agp;	/**< AGP data */
 
-	struct device *dev;             /**< Device structure */
 	struct pci_dev *pdev;		/**< PCI device structure */
 #ifdef __alpha__
 	struct pci_controller *hose;
@@ -1182,17 +1181,11 @@
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
 	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
-	void *dev_private;		/**< device private data */
-	struct address_space *dev_mapping;
 	struct drm_sigdata sigdata;	   /**< For block_all_signals */
 	sigset_t sigmask;
 
-	struct drm_driver *driver;
 	struct drm_local_map *agp_buffer_map;
 	unsigned int agp_buffer_token;
-	struct drm_minor *control;		/**< Control node for card */
-	struct drm_minor *primary;		/**< render type primary screen head */
-	struct drm_minor *render;		/**< render node for card */
 
         struct drm_mode_config mode_config;	/**< Current mode config */
 
@@ -1203,8 +1196,6 @@
 	struct drm_vma_offset_manager *vma_offset_manager;
 	/*@} */
 	int switch_power_state;
-
-	atomic_t unplugged; /* device has been unplugged or gone away */
 };
 
 #define DRM_SWITCH_POWER_ON 0
@@ -1411,20 +1402,6 @@
 extern void drm_calc_timestamping_constants(struct drm_crtc *crtc,
 					    const struct drm_display_mode *mode);
 
-extern bool
-drm_mode_parse_command_line_for_connector(const char *mode_option,
-					  struct drm_connector *connector,
-					  struct drm_cmdline_mode *mode);
-
-extern struct drm_display_mode *
-drm_mode_create_from_cmdline_mode(struct drm_device *dev,
-				  struct drm_cmdline_mode *cmd);
-
-extern int drm_display_mode_from_videomode(const struct videomode *vm,
-					   struct drm_display_mode *dmode);
-extern int of_get_drm_display_mode(struct device_node *np,
-				   struct drm_display_mode *dmode,
-				   int index);
 
 /* Modesetting support */
 extern void drm_vblank_pre_modeset(struct drm_device *dev, int crtc);
@@ -1661,9 +1638,14 @@
 
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
-void drm_dev_free(struct drm_device *dev);
+void drm_dev_ref(struct drm_device *dev);
+void drm_dev_unref(struct drm_device *dev);
 int drm_dev_register(struct drm_device *dev, unsigned long flags);
 void drm_dev_unregister(struct drm_device *dev);
+
+struct drm_minor *drm_minor_acquire(unsigned int minor_id);
+void drm_minor_release(struct drm_minor *minor);
+
 /*@}*/
 
 /* PCI section */
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 8f3dee0..27f828c 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -32,7 +32,6 @@
 #include <linux/fb.h>
 #include <linux/hdmi.h>
 #include <drm/drm_mode.h>
-
 #include <drm/drm_fourcc.h>
 
 struct drm_device;
@@ -65,130 +64,14 @@
 	uint64_t values[DRM_OBJECT_MAX_PROPERTY];
 };
 
-/*
- * Note on terminology:  here, for brevity and convenience, we refer to connector
- * control chips as 'CRTCs'.  They can control any type of connector, VGA, LVDS,
- * DVI, etc.  And 'screen' refers to the whole of the visible display, which
- * may span multiple monitors (and therefore multiple CRTC and connector
- * structures).
- */
-
-enum drm_mode_status {
-    MODE_OK	= 0,	/* Mode OK */
-    MODE_HSYNC,		/* hsync out of range */
-    MODE_VSYNC,		/* vsync out of range */
-    MODE_H_ILLEGAL,	/* mode has illegal horizontal timings */
-    MODE_V_ILLEGAL,	/* mode has illegal horizontal timings */
-    MODE_BAD_WIDTH,	/* requires an unsupported linepitch */
-    MODE_NOMODE,	/* no mode with a matching name */
-    MODE_NO_INTERLACE,	/* interlaced mode not supported */
-    MODE_NO_DBLESCAN,	/* doublescan mode not supported */
-    MODE_NO_VSCAN,	/* multiscan mode not supported */
-    MODE_MEM,		/* insufficient video memory */
-    MODE_VIRTUAL_X,	/* mode width too large for specified virtual size */
-    MODE_VIRTUAL_Y,	/* mode height too large for specified virtual size */
-    MODE_MEM_VIRT,	/* insufficient video memory given virtual size */
-    MODE_NOCLOCK,	/* no fixed clock available */
-    MODE_CLOCK_HIGH,	/* clock required is too high */
-    MODE_CLOCK_LOW,	/* clock required is too low */
-    MODE_CLOCK_RANGE,	/* clock/mode isn't in a ClockRange */
-    MODE_BAD_HVALUE,	/* horizontal timing was out of range */
-    MODE_BAD_VVALUE,	/* vertical timing was out of range */
-    MODE_BAD_VSCAN,	/* VScan value out of range */
-    MODE_HSYNC_NARROW,	/* horizontal sync too narrow */
-    MODE_HSYNC_WIDE,	/* horizontal sync too wide */
-    MODE_HBLANK_NARROW,	/* horizontal blanking too narrow */
-    MODE_HBLANK_WIDE,	/* horizontal blanking too wide */
-    MODE_VSYNC_NARROW,	/* vertical sync too narrow */
-    MODE_VSYNC_WIDE,	/* vertical sync too wide */
-    MODE_VBLANK_NARROW,	/* vertical blanking too narrow */
-    MODE_VBLANK_WIDE,	/* vertical blanking too wide */
-    MODE_PANEL,         /* exceeds panel dimensions */
-    MODE_INTERLACE_WIDTH, /* width too large for interlaced mode */
-    MODE_ONE_WIDTH,     /* only one width is supported */
-    MODE_ONE_HEIGHT,    /* only one height is supported */
-    MODE_ONE_SIZE,      /* only one resolution is supported */
-    MODE_NO_REDUCED,    /* monitor doesn't accept reduced blanking */
-    MODE_NO_STEREO,	/* stereo modes not supported */
-    MODE_UNVERIFIED = -3, /* mode needs to reverified */
-    MODE_BAD = -2,	/* unspecified reason */
-    MODE_ERROR	= -1	/* error condition */
+enum drm_connector_force {
+	DRM_FORCE_UNSPECIFIED,
+	DRM_FORCE_OFF,
+	DRM_FORCE_ON,         /* force on analog part normally */
+	DRM_FORCE_ON_DIGITAL, /* for DVI-I use digital connector */
 };
 
-#define DRM_MODE_TYPE_CLOCK_CRTC_C (DRM_MODE_TYPE_CLOCK_C | \
-				    DRM_MODE_TYPE_CRTC_C)
-
-#define DRM_MODE(nm, t, c, hd, hss, hse, ht, hsk, vd, vss, vse, vt, vs, f) \
-	.name = nm, .status = 0, .type = (t), .clock = (c), \
-	.hdisplay = (hd), .hsync_start = (hss), .hsync_end = (hse), \
-	.htotal = (ht), .hskew = (hsk), .vdisplay = (vd), \
-	.vsync_start = (vss), .vsync_end = (vse), .vtotal = (vt), \
-	.vscan = (vs), .flags = (f), \
-	.base.type = DRM_MODE_OBJECT_MODE
-
-#define CRTC_INTERLACE_HALVE_V	(1 << 0) /* halve V values for interlacing */
-#define CRTC_STEREO_DOUBLE	(1 << 1) /* adjust timings for stereo modes */
-
-#define DRM_MODE_FLAG_3D_MAX	DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF
-
-struct drm_display_mode {
-	/* Header */
-	struct list_head head;
-	struct drm_mode_object base;
-
-	char name[DRM_DISPLAY_MODE_LEN];
-
-	enum drm_mode_status status;
-	unsigned int type;
-
-	/* Proposed mode values */
-	int clock;		/* in kHz */
-	int hdisplay;
-	int hsync_start;
-	int hsync_end;
-	int htotal;
-	int hskew;
-	int vdisplay;
-	int vsync_start;
-	int vsync_end;
-	int vtotal;
-	int vscan;
-	unsigned int flags;
-
-	/* Addressable image size (may be 0 for projectors, etc.) */
-	int width_mm;
-	int height_mm;
-
-	/* Actual mode we give to hw */
-	int crtc_clock;		/* in KHz */
-	int crtc_hdisplay;
-	int crtc_hblank_start;
-	int crtc_hblank_end;
-	int crtc_hsync_start;
-	int crtc_hsync_end;
-	int crtc_htotal;
-	int crtc_hskew;
-	int crtc_vdisplay;
-	int crtc_vblank_start;
-	int crtc_vblank_end;
-	int crtc_vsync_start;
-	int crtc_vsync_end;
-	int crtc_vtotal;
-
-	/* Driver private mode info */
-	int private_size;
-	int *private;
-	int private_flags;
-
-	int vrefresh;		/* in Hz */
-	int hsync;		/* in kHz */
-	enum hdmi_picture_aspect picture_aspect_ratio;
-};
-
-static inline bool drm_mode_is_stereo(const struct drm_display_mode *mode)
-{
-	return mode->flags & DRM_MODE_FLAG_3D_MASK;
-}
+#include <drm/drm_modes.h>
 
 enum drm_connector_status {
 	connector_status_connected = 1,
@@ -540,13 +423,6 @@
 	void *helper_private;
 };
 
-enum drm_connector_force {
-	DRM_FORCE_UNSPECIFIED,
-	DRM_FORCE_OFF,
-	DRM_FORCE_ON,         /* force on analog part normally */
-	DRM_FORCE_ON_DIGITAL, /* for DVI-I use digital connector */
-};
-
 /* should we poll this connector for connects and disconnects */
 /* hot plug detectable */
 #define DRM_CONNECTOR_POLL_HPD (1 << 0)
@@ -994,6 +870,7 @@
 
 extern const char *drm_get_connector_name(const struct drm_connector *connector);
 extern const char *drm_get_connector_status_name(enum drm_connector_status status);
+extern const char *drm_get_subpixel_order_name(enum subpixel_order order);
 extern const char *drm_get_dpms_name(int val);
 extern const char *drm_get_dvi_i_subconnector_name(int val);
 extern const char *drm_get_dvi_i_select_name(int val);
@@ -1006,34 +883,10 @@
 				 struct i2c_adapter *adapter);
 extern struct edid *drm_edid_duplicate(const struct edid *edid);
 extern int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid);
-extern void drm_mode_probed_add(struct drm_connector *connector, struct drm_display_mode *mode);
-extern void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode *src);
-extern struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev,
-						   const struct drm_display_mode *mode);
-extern void drm_mode_debug_printmodeline(const struct drm_display_mode *mode);
 extern void drm_mode_config_init(struct drm_device *dev);
 extern void drm_mode_config_reset(struct drm_device *dev);
 extern void drm_mode_config_cleanup(struct drm_device *dev);
-extern void drm_mode_set_name(struct drm_display_mode *mode);
-extern bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2);
-extern bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2);
-extern int drm_mode_width(const struct drm_display_mode *mode);
-extern int drm_mode_height(const struct drm_display_mode *mode);
 
-/* for us by fb module */
-extern struct drm_display_mode *drm_mode_create(struct drm_device *dev);
-extern void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode);
-extern void drm_mode_validate_size(struct drm_device *dev,
-				   struct list_head *mode_list,
-				   int maxX, int maxY, int maxPitch);
-extern void drm_mode_prune_invalid(struct drm_device *dev,
-				   struct list_head *mode_list, bool verbose);
-extern void drm_mode_sort(struct list_head *mode_list);
-extern int drm_mode_hsync(const struct drm_display_mode *mode);
-extern int drm_mode_vrefresh(const struct drm_display_mode *mode);
-extern void drm_mode_set_crtcinfo(struct drm_display_mode *p,
-				  int adjust_flags);
-extern void drm_mode_connector_list_update(struct drm_connector *connector);
 extern int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 						struct edid *edid);
 extern int drm_object_property_set_value(struct drm_mode_object *obj,
@@ -1081,8 +934,6 @@
 
 extern int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 					     struct drm_encoder *encoder);
-extern void drm_mode_connector_detach_encoder(struct drm_connector *connector,
-					   struct drm_encoder *encoder);
 extern int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc,
 					 int gamma_size);
 extern struct drm_mode_object *drm_mode_object_find(struct drm_device *dev,
@@ -1137,16 +988,6 @@
 extern bool drm_rgb_quant_range_selectable(struct edid *edid);
 extern int drm_mode_page_flip_ioctl(struct drm_device *dev,
 				    void *data, struct drm_file *file_priv);
-extern struct drm_display_mode *drm_cvt_mode(struct drm_device *dev,
-				int hdisplay, int vdisplay, int vrefresh,
-				bool reduced, bool interlaced, bool margins);
-extern struct drm_display_mode *drm_gtf_mode(struct drm_device *dev,
-				int hdisplay, int vdisplay, int vrefresh,
-				bool interlaced, int margins);
-extern struct drm_display_mode *drm_gtf_mode_complex(struct drm_device *dev,
-				int hdisplay, int vdisplay, int vrefresh,
-				bool interlaced, int margins, int GTF_M,
-				int GTF_2C, int GTF_K, int GTF_2J);
 extern int drm_add_modes_noedid(struct drm_connector *connector,
 				int hdisplay, int vdisplay);
 extern void drm_set_preferred_mode(struct drm_connector *connector,
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index b1388b5..0bb34ca 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -139,8 +139,8 @@
 
 extern void drm_helper_move_panel_connectors_to_head(struct drm_device *);
 
-extern int drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
-					  struct drm_mode_fb_cmd2 *mode_cmd);
+extern void drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
+					   struct drm_mode_fb_cmd2 *mode_cmd);
 
 static inline void drm_crtc_helper_add(struct drm_crtc *crtc,
 				       const struct drm_crtc_helper_funcs *funcs)
@@ -160,7 +160,7 @@
 	connector->helper_private = (void *)funcs;
 }
 
-extern int drm_helper_resume_force_mode(struct drm_device *dev);
+extern void drm_helper_resume_force_mode(struct drm_device *dev);
 extern void drm_kms_helper_poll_init(struct drm_device *dev);
 extern void drm_kms_helper_poll_fini(struct drm_device *dev);
 extern bool drm_helper_hpd_irq_event(struct drm_device *dev);
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 471f276..2d659dc 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -121,5 +121,11 @@
 int drm_fb_helper_single_add_all_connectors(struct drm_fb_helper *fb_helper);
 int drm_fb_helper_debug_enter(struct fb_info *info);
 int drm_fb_helper_debug_leave(struct fb_info *info);
+struct drm_display_mode *
+drm_has_preferred_mode(struct drm_fb_helper_connector *fb_connector,
+			int width, int height);
+struct drm_display_mode *
+drm_pick_cmdline_mode(struct drm_fb_helper_connector *fb_helper_conn,
+		      int width, int height);
 
 #endif
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index cba6786..8b6981a 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -85,11 +85,31 @@
 			     unsigned long *start, unsigned long *end);
 };
 
+/**
+ * drm_mm_node_allocated - checks whether a node is allocated
+ * @node: drm_mm_node to check
+ *
+ * Drivers should use this helpers for proper encapusulation of drm_mm
+ * internals.
+ *
+ * Returns:
+ * True if the @node is allocated.
+ */
 static inline bool drm_mm_node_allocated(struct drm_mm_node *node)
 {
 	return node->allocated;
 }
 
+/**
+ * drm_mm_initialized - checks whether an allocator is initialized
+ * @mm: drm_mm to check
+ *
+ * Drivers should use this helpers for proper encapusulation of drm_mm
+ * internals.
+ *
+ * Returns:
+ * True if the @mm is initialized.
+ */
 static inline bool drm_mm_initialized(struct drm_mm *mm)
 {
 	return mm->hole_stack.next;
@@ -100,6 +120,17 @@
 	return hole_node->start + hole_node->size;
 }
 
+/**
+ * drm_mm_hole_node_start - computes the start of the hole following @node
+ * @hole_node: drm_mm_node which implicitly tracks the following hole
+ *
+ * This is useful for driver-sepific debug dumpers. Otherwise drivers should not
+ * inspect holes themselves. Drivers must check first whether a hole indeed
+ * follows by looking at node->hole_follows.
+ *
+ * Returns:
+ * Start of the subsequent hole.
+ */
 static inline unsigned long drm_mm_hole_node_start(struct drm_mm_node *hole_node)
 {
 	BUG_ON(!hole_node->hole_follows);
@@ -112,18 +143,49 @@
 			  struct drm_mm_node, node_list)->start;
 }
 
+/**
+ * drm_mm_hole_node_end - computes the end of the hole following @node
+ * @hole_node: drm_mm_node which implicitly tracks the following hole
+ *
+ * This is useful for driver-sepific debug dumpers. Otherwise drivers should not
+ * inspect holes themselves. Drivers must check first whether a hole indeed
+ * follows by looking at node->hole_follows.
+ *
+ * Returns:
+ * End of the subsequent hole.
+ */
 static inline unsigned long drm_mm_hole_node_end(struct drm_mm_node *hole_node)
 {
 	return __drm_mm_hole_node_end(hole_node);
 }
 
+/**
+ * drm_mm_for_each_node - iterator to walk over all allocated nodes
+ * @entry: drm_mm_node structure to assign to in each iteration step
+ * @mm: drm_mm allocator to walk
+ *
+ * This iterator walks over all nodes in the range allocator. It is implemented
+ * with list_for_each, so not save against removal of elements.
+ */
 #define drm_mm_for_each_node(entry, mm) list_for_each_entry(entry, \
 						&(mm)->head_node.node_list, \
 						node_list)
 
-/* Note that we need to unroll list_for_each_entry in order to inline
- * setting hole_start and hole_end on each iteration and keep the
- * macro sane.
+/**
+ * drm_mm_for_each_hole - iterator to walk over all holes
+ * @entry: drm_mm_node used internally to track progress
+ * @mm: drm_mm allocator to walk
+ * @hole_start: ulong variable to assign the hole start to on each iteration
+ * @hole_end: ulong variable to assign the hole end to on each iteration
+ *
+ * This iterator walks over all holes in the range allocator. It is implemented
+ * with list_for_each, so not save against removal of elements. @entry is used
+ * internally and will not reflect a real drm_mm_node for the very first hole.
+ * Hence users of this iterator may not access it.
+ *
+ * Implementation Note:
+ * We need to inline list_for_each_entry in order to be able to set hole_start
+ * and hole_end on each iteration while keeping the macro sane.
  */
 #define drm_mm_for_each_hole(entry, mm, hole_start, hole_end) \
 	for (entry = list_entry((mm)->hole_stack.next, struct drm_mm_node, hole_stack); \
@@ -136,14 +198,30 @@
 /*
  * Basic range manager support (drm_mm.c)
  */
-extern int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node);
+int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node);
 
-extern int drm_mm_insert_node_generic(struct drm_mm *mm,
-				      struct drm_mm_node *node,
-				      unsigned long size,
-				      unsigned alignment,
-				      unsigned long color,
-				      enum drm_mm_search_flags flags);
+int drm_mm_insert_node_generic(struct drm_mm *mm,
+			       struct drm_mm_node *node,
+			       unsigned long size,
+			       unsigned alignment,
+			       unsigned long color,
+			       enum drm_mm_search_flags flags);
+/**
+ * drm_mm_insert_node - search for space and insert @node
+ * @mm: drm_mm to allocate from
+ * @node: preallocate node to insert
+ * @size: size of the allocation
+ * @alignment: alignment of the allocation
+ * @flags: flags to fine-tune the allocation
+ *
+ * This is a simplified version of drm_mm_insert_node_generic() with @color set
+ * to 0.
+ *
+ * The preallocated node must be cleared to 0.
+ *
+ * Returns:
+ * 0 on success, -ENOSPC if there's no suitable hole.
+ */
 static inline int drm_mm_insert_node(struct drm_mm *mm,
 				     struct drm_mm_node *node,
 				     unsigned long size,
@@ -153,14 +231,32 @@
 	return drm_mm_insert_node_generic(mm, node, size, alignment, 0, flags);
 }
 
-extern int drm_mm_insert_node_in_range_generic(struct drm_mm *mm,
-				       struct drm_mm_node *node,
-				       unsigned long size,
-				       unsigned alignment,
-				       unsigned long color,
-				       unsigned long start,
-				       unsigned long end,
-				       enum drm_mm_search_flags flags);
+int drm_mm_insert_node_in_range_generic(struct drm_mm *mm,
+					struct drm_mm_node *node,
+					unsigned long size,
+					unsigned alignment,
+					unsigned long color,
+					unsigned long start,
+					unsigned long end,
+					enum drm_mm_search_flags flags);
+/**
+ * drm_mm_insert_node_in_range - ranged search for space and insert @node
+ * @mm: drm_mm to allocate from
+ * @node: preallocate node to insert
+ * @size: size of the allocation
+ * @alignment: alignment of the allocation
+ * @start: start of the allowed range for this node
+ * @end: end of the allowed range for this node
+ * @flags: flags to fine-tune the allocation
+ *
+ * This is a simplified version of drm_mm_insert_node_in_range_generic() with
+ * @color set to 0.
+ *
+ * The preallocated node must be cleared to 0.
+ *
+ * Returns:
+ * 0 on success, -ENOSPC if there's no suitable hole.
+ */
 static inline int drm_mm_insert_node_in_range(struct drm_mm *mm,
 					      struct drm_mm_node *node,
 					      unsigned long size,
@@ -173,13 +269,13 @@
 						   0, start, end, flags);
 }
 
-extern void drm_mm_remove_node(struct drm_mm_node *node);
-extern void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new);
-extern void drm_mm_init(struct drm_mm *mm,
-			unsigned long start,
-			unsigned long size);
-extern void drm_mm_takedown(struct drm_mm *mm);
-extern int drm_mm_clean(struct drm_mm *mm);
+void drm_mm_remove_node(struct drm_mm_node *node);
+void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new);
+void drm_mm_init(struct drm_mm *mm,
+		 unsigned long start,
+		 unsigned long size);
+void drm_mm_takedown(struct drm_mm *mm);
+bool drm_mm_clean(struct drm_mm *mm);
 
 void drm_mm_init_scan(struct drm_mm *mm,
 		      unsigned long size,
@@ -191,10 +287,10 @@
 				 unsigned long color,
 				 unsigned long start,
 				 unsigned long end);
-int drm_mm_scan_add_block(struct drm_mm_node *node);
-int drm_mm_scan_remove_block(struct drm_mm_node *node);
+bool drm_mm_scan_add_block(struct drm_mm_node *node);
+bool drm_mm_scan_remove_block(struct drm_mm_node *node);
 
-extern void drm_mm_debug_table(struct drm_mm *mm, const char *prefix);
+void drm_mm_debug_table(struct drm_mm *mm, const char *prefix);
 #ifdef CONFIG_DEBUG_FS
 int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm);
 #endif
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
new file mode 100644
index 0000000..2dbbf99
--- /dev/null
+++ b/include/drm/drm_modes.h
@@ -0,0 +1,237 @@
+/*
+ * Copyright © 2006 Keith Packard
+ * Copyright © 2007-2008 Dave Airlie
+ * Copyright © 2007-2008 Intel Corporation
+ *   Jesse Barnes <jesse.barnes@intel.com>
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * 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.
+ */
+#ifndef __DRM_MODES_H__
+#define __DRM_MODES_H__
+
+/*
+ * Note on terminology:  here, for brevity and convenience, we refer to connector
+ * control chips as 'CRTCs'.  They can control any type of connector, VGA, LVDS,
+ * DVI, etc.  And 'screen' refers to the whole of the visible display, which
+ * may span multiple monitors (and therefore multiple CRTC and connector
+ * structures).
+ */
+
+enum drm_mode_status {
+    MODE_OK	= 0,	/* Mode OK */
+    MODE_HSYNC,		/* hsync out of range */
+    MODE_VSYNC,		/* vsync out of range */
+    MODE_H_ILLEGAL,	/* mode has illegal horizontal timings */
+    MODE_V_ILLEGAL,	/* mode has illegal horizontal timings */
+    MODE_BAD_WIDTH,	/* requires an unsupported linepitch */
+    MODE_NOMODE,	/* no mode with a matching name */
+    MODE_NO_INTERLACE,	/* interlaced mode not supported */
+    MODE_NO_DBLESCAN,	/* doublescan mode not supported */
+    MODE_NO_VSCAN,	/* multiscan mode not supported */
+    MODE_MEM,		/* insufficient video memory */
+    MODE_VIRTUAL_X,	/* mode width too large for specified virtual size */
+    MODE_VIRTUAL_Y,	/* mode height too large for specified virtual size */
+    MODE_MEM_VIRT,	/* insufficient video memory given virtual size */
+    MODE_NOCLOCK,	/* no fixed clock available */
+    MODE_CLOCK_HIGH,	/* clock required is too high */
+    MODE_CLOCK_LOW,	/* clock required is too low */
+    MODE_CLOCK_RANGE,	/* clock/mode isn't in a ClockRange */
+    MODE_BAD_HVALUE,	/* horizontal timing was out of range */
+    MODE_BAD_VVALUE,	/* vertical timing was out of range */
+    MODE_BAD_VSCAN,	/* VScan value out of range */
+    MODE_HSYNC_NARROW,	/* horizontal sync too narrow */
+    MODE_HSYNC_WIDE,	/* horizontal sync too wide */
+    MODE_HBLANK_NARROW,	/* horizontal blanking too narrow */
+    MODE_HBLANK_WIDE,	/* horizontal blanking too wide */
+    MODE_VSYNC_NARROW,	/* vertical sync too narrow */
+    MODE_VSYNC_WIDE,	/* vertical sync too wide */
+    MODE_VBLANK_NARROW,	/* vertical blanking too narrow */
+    MODE_VBLANK_WIDE,	/* vertical blanking too wide */
+    MODE_PANEL,         /* exceeds panel dimensions */
+    MODE_INTERLACE_WIDTH, /* width too large for interlaced mode */
+    MODE_ONE_WIDTH,     /* only one width is supported */
+    MODE_ONE_HEIGHT,    /* only one height is supported */
+    MODE_ONE_SIZE,      /* only one resolution is supported */
+    MODE_NO_REDUCED,    /* monitor doesn't accept reduced blanking */
+    MODE_NO_STEREO,	/* stereo modes not supported */
+    MODE_UNVERIFIED = -3, /* mode needs to reverified */
+    MODE_BAD = -2,	/* unspecified reason */
+    MODE_ERROR	= -1	/* error condition */
+};
+
+#define DRM_MODE_TYPE_CLOCK_CRTC_C (DRM_MODE_TYPE_CLOCK_C | \
+				    DRM_MODE_TYPE_CRTC_C)
+
+#define DRM_MODE(nm, t, c, hd, hss, hse, ht, hsk, vd, vss, vse, vt, vs, f) \
+	.name = nm, .status = 0, .type = (t), .clock = (c), \
+	.hdisplay = (hd), .hsync_start = (hss), .hsync_end = (hse), \
+	.htotal = (ht), .hskew = (hsk), .vdisplay = (vd), \
+	.vsync_start = (vss), .vsync_end = (vse), .vtotal = (vt), \
+	.vscan = (vs), .flags = (f), \
+	.base.type = DRM_MODE_OBJECT_MODE
+
+#define CRTC_INTERLACE_HALVE_V	(1 << 0) /* halve V values for interlacing */
+#define CRTC_STEREO_DOUBLE	(1 << 1) /* adjust timings for stereo modes */
+
+#define DRM_MODE_FLAG_3D_MAX	DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF
+
+struct drm_display_mode {
+	/* Header */
+	struct list_head head;
+	struct drm_mode_object base;
+
+	char name[DRM_DISPLAY_MODE_LEN];
+
+	enum drm_mode_status status;
+	unsigned int type;
+
+	/* Proposed mode values */
+	int clock;		/* in kHz */
+	int hdisplay;
+	int hsync_start;
+	int hsync_end;
+	int htotal;
+	int hskew;
+	int vdisplay;
+	int vsync_start;
+	int vsync_end;
+	int vtotal;
+	int vscan;
+	unsigned int flags;
+
+	/* Addressable image size (may be 0 for projectors, etc.) */
+	int width_mm;
+	int height_mm;
+
+	/* Actual mode we give to hw */
+	int crtc_clock;		/* in KHz */
+	int crtc_hdisplay;
+	int crtc_hblank_start;
+	int crtc_hblank_end;
+	int crtc_hsync_start;
+	int crtc_hsync_end;
+	int crtc_htotal;
+	int crtc_hskew;
+	int crtc_vdisplay;
+	int crtc_vblank_start;
+	int crtc_vblank_end;
+	int crtc_vsync_start;
+	int crtc_vsync_end;
+	int crtc_vtotal;
+
+	/* Driver private mode info */
+	int *private;
+	int private_flags;
+
+	int vrefresh;		/* in Hz */
+	int hsync;		/* in kHz */
+	enum hdmi_picture_aspect picture_aspect_ratio;
+};
+
+/* mode specified on the command line */
+struct drm_cmdline_mode {
+	bool specified;
+	bool refresh_specified;
+	bool bpp_specified;
+	int xres, yres;
+	int bpp;
+	int refresh;
+	bool rb;
+	bool interlace;
+	bool cvt;
+	bool margins;
+	enum drm_connector_force force;
+};
+
+/**
+ * drm_mode_is_stereo - check for stereo mode flags
+ * @mode: drm_display_mode to check
+ *
+ * Returns:
+ * True if the mode is one of the stereo modes (like side-by-side), false if
+ * not.
+ */
+static inline bool drm_mode_is_stereo(const struct drm_display_mode *mode)
+{
+	return mode->flags & DRM_MODE_FLAG_3D_MASK;
+}
+
+struct drm_connector;
+struct drm_cmdline_mode;
+
+struct drm_display_mode *drm_mode_create(struct drm_device *dev);
+void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode);
+void drm_mode_probed_add(struct drm_connector *connector, struct drm_display_mode *mode);
+void drm_mode_debug_printmodeline(const struct drm_display_mode *mode);
+
+struct drm_display_mode *drm_cvt_mode(struct drm_device *dev,
+				      int hdisplay, int vdisplay, int vrefresh,
+				      bool reduced, bool interlaced,
+				      bool margins);
+struct drm_display_mode *drm_gtf_mode(struct drm_device *dev,
+				      int hdisplay, int vdisplay, int vrefresh,
+				      bool interlaced, int margins);
+struct drm_display_mode *drm_gtf_mode_complex(struct drm_device *dev,
+					      int hdisplay, int vdisplay,
+					      int vrefresh, bool interlaced,
+					      int margins,
+					      int GTF_M, int GTF_2C,
+					      int GTF_K, int GTF_2J);
+void drm_display_mode_from_videomode(const struct videomode *vm,
+				     struct drm_display_mode *dmode);
+int of_get_drm_display_mode(struct device_node *np,
+			    struct drm_display_mode *dmode,
+			    int index);
+
+void drm_mode_set_name(struct drm_display_mode *mode);
+int drm_mode_hsync(const struct drm_display_mode *mode);
+int drm_mode_vrefresh(const struct drm_display_mode *mode);
+
+void drm_mode_set_crtcinfo(struct drm_display_mode *p,
+			   int adjust_flags);
+void drm_mode_copy(struct drm_display_mode *dst,
+		   const struct drm_display_mode *src);
+struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev,
+					    const struct drm_display_mode *mode);
+bool drm_mode_equal(const struct drm_display_mode *mode1,
+		    const struct drm_display_mode *mode2);
+bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1,
+					const struct drm_display_mode *mode2);
+
+/* for use by the crtc helper probe functions */
+void drm_mode_validate_size(struct drm_device *dev,
+			    struct list_head *mode_list,
+			    int maxX, int maxY);
+void drm_mode_prune_invalid(struct drm_device *dev,
+			    struct list_head *mode_list, bool verbose);
+void drm_mode_sort(struct list_head *mode_list);
+void drm_mode_connector_list_update(struct drm_connector *connector);
+
+/* parsing cmdline modes */
+bool
+drm_mode_parse_command_line_for_connector(const char *mode_option,
+					  struct drm_connector *connector,
+					  struct drm_cmdline_mode *mode);
+struct drm_display_mode *
+drm_mode_create_from_cmdline_mode(struct drm_device *dev,
+				  struct drm_cmdline_mode *cmd);
+
+#endif /* __DRM_MODES_H__ */
diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h
index c18a593..8cd402c 100644
--- a/include/drm/drm_vma_manager.h
+++ b/include/drm/drm_vma_manager.h
@@ -221,8 +221,8 @@
  * @file_mapping: Address space to unmap @node from
  *
  * Unmap all userspace mappings for a given offset node. The mappings must be
- * associated with the @file_mapping address-space. If no offset exists or
- * the address-space is invalid, nothing is done.
+ * associated with the @file_mapping address-space. If no offset exists
+ * nothing is done.
  *
  * This call is unlocked. The caller must guarantee that drm_vma_offset_remove()
  * is not called on this node concurrently.
@@ -230,7 +230,7 @@
 static inline void drm_vma_node_unmap(struct drm_vma_offset_node *node,
 				      struct address_space *file_mapping)
 {
-	if (file_mapping && drm_vma_node_has_offset(node))
+	if (drm_vma_node_has_offset(node))
 		unmap_mapping_range(file_mapping,
 				    drm_vma_node_offset_addr(node),
 				    drm_vma_node_size(node) << PAGE_SHIFT, 1);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 32d34eb..5d8aabe 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -747,6 +747,7 @@
  * @bdev: A pointer to a struct ttm_bo_device to initialize.
  * @glob: A pointer to an initialized struct ttm_bo_global.
  * @driver: A pointer to a struct ttm_bo_driver set up by the caller.
+ * @mapping: The address space to use for this bo.
  * @file_page_offset: Offset into the device address space that is available
  * for buffer data. This ensures compatibility with other users of the
  * address space.
@@ -758,6 +759,7 @@
 extern int ttm_bo_device_init(struct ttm_bo_device *bdev,
 			      struct ttm_bo_global *glob,
 			      struct ttm_bo_driver *driver,
+			      struct address_space *mapping,
 			      uint64_t file_page_offset, bool need_dma32);
 
 /**
diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index a1116a3..8c1603b 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -36,10 +36,10 @@
 #define TEGRA124_CLK_PWM 17
 #define TEGRA124_CLK_I2S2 18
 /* 20 (register bit affects vi and vi_sensor) */
-#define TEGRA124_CLK_GR_2D 21
+/* 21 */
 #define TEGRA124_CLK_USBD 22
 #define TEGRA124_CLK_ISP 23
-#define TEGRA124_CLK_GR_3D 24
+/* 26 */
 /* 25 */
 #define TEGRA124_CLK_DISP2 26
 #define TEGRA124_CLK_DISP1 27
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index be85127..f27000f 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -171,6 +171,11 @@
 	return 0;
 }
 
+static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+	return -ENXIO;
+}
+
 static inline int kvm_vgic_init(struct kvm *kvm)
 {
 	return 0;
diff --git a/include/linux/audit.h b/include/linux/audit.h
index aa865a9..ec1464d 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -43,6 +43,7 @@
 struct mqstat;
 struct audit_watch;
 struct audit_tree;
+struct sk_buff;
 
 struct audit_krule {
 	int			vers_ops;
@@ -463,7 +464,7 @@
 extern int audit_filter_type(int type);
 extern int audit_rule_change(int type, __u32 portid, int seq,
 				void *data, size_t datasz);
-extern int audit_list_rules_send(__u32 portid, int seq);
+extern int audit_list_rules_send(struct sk_buff *request_skb, int seq);
 
 extern u32 audit_enabled;
 #else /* CONFIG_AUDIT */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 18ba8a6..2ff2e8d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -121,8 +121,7 @@
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request_queue *, struct request *,
-		bool, bool);
+void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
@@ -134,7 +133,13 @@
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int);
 void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int);
 
-void blk_mq_end_io(struct request *rq, int error);
+bool blk_mq_end_io_partial(struct request *rq, int error,
+		unsigned int nr_bytes);
+static inline void blk_mq_end_io(struct request *rq, int error)
+{
+	bool done = !blk_mq_end_io_partial(rq, error, blk_rq_bytes(rq));
+	BUG_ON(!done);
+}
 
 void blk_mq_complete_request(struct request *rq);
 
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 092b641..4a21a87 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -245,6 +245,10 @@
 void omap2_init_clk_clkdm(struct clk_hw *clk);
 unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 				    unsigned long parent_rate);
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate);
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *prate);
 int omap2_clkops_enable_clkdm(struct clk_hw *hw);
 void omap2_clkops_disable_clkdm(struct clk_hw *hw);
 int omap2_clk_disable_autoidle_all(void);
diff --git a/include/linux/file.h b/include/linux/file.h
index cbacf4f..4d69123 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -28,33 +28,36 @@
 
 struct fd {
 	struct file *file;
-	int need_put;
+	unsigned int flags;
 };
+#define FDPUT_FPUT       1
+#define FDPUT_POS_UNLOCK 2
 
 static inline void fdput(struct fd fd)
 {
-	if (fd.need_put)
+	if (fd.flags & FDPUT_FPUT)
 		fput(fd.file);
 }
 
 extern struct file *fget(unsigned int fd);
-extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern unsigned long __fdget(unsigned int fd);
+extern unsigned long __fdget_raw(unsigned int fd);
+extern unsigned long __fdget_pos(unsigned int fd);
+
+static inline struct fd __to_fd(unsigned long v)
+{
+	return (struct fd){(struct file *)(v & ~3),v & 3};
+}
 
 static inline struct fd fdget(unsigned int fd)
 {
-	int b;
-	struct file *f = fget_light(fd, &b);
-	return (struct fd){f,b};
+	return __to_fd(__fdget(fd));
 }
 
-extern struct file *fget_raw(unsigned int fd);
-extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
-
 static inline struct fd fdget_raw(unsigned int fd)
 {
-	int b;
-	struct file *f = fget_raw_light(fd, &b);
-	return (struct fd){f,b};
+	return __to_fd(__fdget_raw(fd));
 }
 
 extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 5d7782e..c3683bd 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -200,6 +200,7 @@
 	unsigned irmc:1;
 	unsigned bc_implemented:2;
 
+	work_func_t workfn;
 	struct delayed_work work;
 	struct fw_attribute_group attribute_group;
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6082956..23b2a35 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -123,6 +123,9 @@
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)0x4000)
 
+/* File needs atomic accesses to f_pos */
+#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
 
@@ -780,13 +783,14 @@
 	const struct file_operations	*f_op;
 
 	/*
-	 * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+	 * Protects f_ep_links, f_flags.
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
+	struct mutex		f_pos_lock;
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	const struct cred	*f_cred;
@@ -808,7 +812,7 @@
 #ifdef CONFIG_DEBUG_WRITECOUNT
 	unsigned long f_mnt_write_state;
 #endif
-};
+} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
 	__u32 handle_bytes;
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 3d286ff..64cf3ef 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -99,7 +99,7 @@
 			    struct fsnotify_mark *inode_mark,
 			    struct fsnotify_mark *vfsmount_mark,
 			    u32 mask, void *data, int data_type,
-			    const unsigned char *file_name);
+			    const unsigned char *file_name, u32 cookie);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
 	void (*free_event)(struct fsnotify_event *event);
@@ -160,7 +160,7 @@
 
 	struct fasync_struct *fsn_fa;    /* async notification */
 
-	struct fsnotify_event overflow_event;	/* Event we queue when the
+	struct fsnotify_event *overflow_event;	/* Event we queue when the
 						 * notification list is too
 						 * full */
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0437439..39b81dc 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -123,6 +123,10 @@
 			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
 			 __GFP_NO_KSWAPD)
 
+/*
+ * GFP_THISNODE does not perform any reclaim, you most likely want to
+ * use __GFP_THISNODE to allocate from a given node without fallback!
+ */
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
 #else
diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 9231be9..11c0182 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -262,6 +262,18 @@
 	struct hdmi_vendor_infoframe hdmi;
 };
 
+/**
+ * union hdmi_infoframe - overall union of all abstract infoframe representations
+ * @any: generic infoframe
+ * @avi: avi infoframe
+ * @spd: spd infoframe
+ * @vendor: union of all vendor infoframes
+ * @audio: audio infoframe
+ *
+ * This is used by the generic pack function. This works since all infoframes
+ * have the same header which also indicates which type of infoframe should be
+ * packed.
+ */
 union hdmi_infoframe {
 	struct hdmi_any_infoframe any;
 	struct hdmi_avi_infoframe avi;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index db51201..b826239 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -157,46 +157,6 @@
 		return HPAGE_PMD_NR;
 	return 1;
 }
-/*
- * compound_trans_head() should be used instead of compound_head(),
- * whenever the "page" passed as parameter could be the tail of a
- * transparent hugepage that could be undergoing a
- * __split_huge_page_refcount(). The page structure layout often
- * changes across releases and it makes extensive use of unions. So if
- * the page structure layout will change in a way that
- * page->first_page gets clobbered by __split_huge_page_refcount, the
- * implementation making use of smp_rmb() will be required.
- *
- * Currently we define compound_trans_head as compound_head, because
- * page->private is in the same union with page->first_page, and
- * page->private isn't clobbered. However this also means we're
- * currently leaving dirt into the page->private field of anonymous
- * pages resulting from a THP split, instead of setting page->private
- * to zero like for every other page that has PG_private not set. But
- * anonymous pages don't use page->private so this is not a problem.
- */
-#if 0
-/* This will be needed if page->private will be clobbered in split_huge_page */
-static inline struct page *compound_trans_head(struct page *page)
-{
-	if (PageTail(page)) {
-		struct page *head;
-		head = page->first_page;
-		smp_rmb();
-		/*
-		 * head may be a dangling pointer.
-		 * __split_huge_page_refcount clears PageTail before
-		 * overwriting first_page, so if PageTail is still
-		 * there it means the head pointer isn't dangling.
-		 */
-		if (PageTail(page))
-			return head;
-	}
-	return page;
-}
-#else
-#define compound_trans_head(page) compound_head(page)
-#endif
 
 extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
@@ -226,7 +186,6 @@
 	do { } while (0)
 #define split_huge_page_pmd_mm(__mm, __address, __pmd)	\
 	do { } while (0)
-#define compound_trans_head(page) compound_head(page)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
 				   unsigned long *vm_flags, int advice)
 {
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index e7831d2..35e7eca 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -118,9 +118,7 @@
  *     the new maximum will handle anyone else.  I may have to revisit this
  *     in the future.
  */
-#define MIN_QUEUESMAX			1
 #define DFLT_QUEUESMAX		      256
-#define HARD_QUEUESMAX		     1024
 #define MIN_MSGMAX			1
 #define DFLT_MSG		       10U
 #define DFLT_MSGMAX		       10
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5be9f02..d267623 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -249,7 +249,8 @@
 
 const void *kernfs_super_ns(struct super_block *sb);
 struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-			       struct kernfs_root *root, const void *ns);
+			       struct kernfs_root *root, bool *new_sb_created,
+			       const void *ns);
 void kernfs_kill_sb(struct super_block *sb);
 
 void kernfs_init(void);
@@ -317,7 +318,7 @@
 
 static inline struct dentry *
 kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-		struct kernfs_root *root, const void *ns)
+		struct kernfs_root *root, bool *new_sb_created, const void *ns)
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_kill_sb(struct super_block *sb) { }
@@ -368,9 +369,9 @@
 
 static inline struct dentry *
 kernfs_mount(struct file_system_type *fs_type, int flags,
-	     struct kernfs_root *root)
+	     struct kernfs_root *root, bool *new_sb_created)
 {
-	return kernfs_mount_ns(fs_type, flags, root, NULL);
+	return kernfs_mount_ns(fs_type, flags, root, new_sb_created, NULL);
 }
 
 #endif	/* __LINUX_KERNFS_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46e..c1b7414 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -175,7 +175,7 @@
  * Special vmas that are non-mergable, non-mlock()able.
  * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
  */
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP)
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
 /*
  * mapping from the currently active vm_flags protection bits (the
@@ -399,8 +399,18 @@
 
 static inline struct page *compound_head(struct page *page)
 {
-	if (unlikely(PageTail(page)))
-		return page->first_page;
+	if (unlikely(PageTail(page))) {
+		struct page *head = page->first_page;
+
+		/*
+		 * page->first_page may be a dangling pointer to an old
+		 * compound page, so recheck that it is still a tail
+		 * page before returning.
+		 */
+		smp_rmb();
+		if (likely(PageTail(page)))
+			return head;
+	}
 	return page;
 }
 
@@ -757,7 +767,7 @@
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
-	return xchg(&page->_last_cpupid, cpupid);
+	return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
 }
 
 static inline int page_cpupid_last(struct page *page)
@@ -766,7 +776,7 @@
 }
 static inline void page_cpupid_reset_last(struct page *page)
 {
-	page->_last_cpupid = -1;
+	page->_last_cpupid = -1 & LAST_CPUPID_MASK;
 }
 #else
 static inline int page_cpupid_last(struct page *page)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5f2052c..9b61b9b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -590,10 +590,10 @@
 
 /*
  * The NUMA zonelists are doubled because we need zonelists that restrict the
- * allocations to a single node for GFP_THISNODE.
+ * allocations to a single node for __GFP_THISNODE.
  *
  * [0]	: Zonelist with fallback
- * [1]	: No fallback (GFP_THISNODE)
+ * [1]	: No fallback (__GFP_THISNODE)
  */
 #define MAX_ZONELISTS 2
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b2fb167..5624e4e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -467,9 +467,14 @@
 };
 
 struct nfs_release_lockowner_args {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_lowner	lock_owner;
 };
 
+struct nfs_release_lockowner_res {
+	struct nfs4_sequence_res	seq_res;
+};
+
 struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3ebbbe7..5e1e6f2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2725,7 +2725,7 @@
 
 static inline void nf_reset_trace(struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
 	skb->nf_trace = 0;
 #endif
 }
@@ -2742,6 +2742,9 @@
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);
 #endif
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
+	dst->nf_trace = src->nf_trace;
+#endif
 }
 
 static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9260abd..b5b2df6 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -410,7 +410,7 @@
  *
  * %GFP_NOWAIT - Allocation will not sleep.
  *
- * %GFP_THISNODE - Allocate node-local memory only.
+ * %__GFP_THISNODE - Allocate node-local memory only.
  *
  * %GFP_DMA - Allocation suitable for DMA.
  *   Should only be used for kmalloc() caches. Otherwise, use a
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index accc497..7159a0a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -60,6 +60,12 @@
 	unsigned int num_tracepoints;
 	struct tracepoint * const *tracepoints_ptrs;
 };
+bool trace_module_has_bad_taint(struct module *mod);
+#else
+static inline bool trace_module_has_bad_taint(struct module *mod)
+{
+	return false;
+}
 #endif /* CONFIG_MODULES */
 
 struct tracepoint_iter {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fc0e432..021b8a3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -97,7 +97,7 @@
 int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 				  enum wb_reason reason);
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this);
+void sync_inodes_sb(struct super_block *);
 void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 void inode_wait_for_writeback(struct inode *inode);
 
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 48ed75c..e77c104 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -129,6 +129,7 @@
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p);
 void ip_tunnel_setup(struct net_device *dev, int net_id);
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
 
 /* Extract dsfield from inner protocol */
 static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
diff --git a/include/net/sock.h b/include/net/sock.h
index 5c3f7c3..b9586a1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1488,6 +1488,11 @@
  */
 #define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
 
+static inline void sock_release_ownership(struct sock *sk)
+{
+	sk->sk_lock.owned = 0;
+}
+
 /*
  * Macro so as to not evaluate some arguments when
  * lockdep is not enabled.
@@ -2186,7 +2191,6 @@
 {
 #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)	| \
 			   (1UL << SOCK_TIMESTAMPING_SOFTWARE)		| \
 			   (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE)	| \
 			   (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 56fc366..8c4dd63 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1303,7 +1303,8 @@
 	/* Fast Open cookie. Size 0 means a cookie request */
 	struct tcp_fastopen_cookie	cookie;
 	struct msghdr			*data;  /* data in MSG_FASTOPEN */
-	u16				copied;	/* queued in tcp_connect() */
+	size_t				size;
+	int				copied;	/* queued in tcp_connect() */
 };
 void tcp_free_fastopen_req(struct tcp_sock *tp);
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index afa5730..fb5654a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1648,6 +1648,11 @@
 }
 #endif
 
+static inline int aead_len(struct xfrm_algo_aead *alg)
+{
+	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
+}
+
 static inline int xfrm_alg_len(const struct xfrm_algo *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
@@ -1686,6 +1691,12 @@
 	return 0;
 }
 
+static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig)
+{
+	return kmemdup(orig, aead_len(orig), GFP_KERNEL);
+}
+
+
 static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig)
 {
 	return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL);
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 68d92e3..6e89ef6 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -449,14 +449,22 @@
 /* dapm audio pin control and status */
 int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm,
 			    const char *pin);
+int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				     const char *pin);
 int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm,
 			     const char *pin);
+int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				      const char *pin);
 int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin);
+int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				 const char *pin);
 int snd_soc_dapm_get_pin_status(struct snd_soc_dapm_context *dapm,
 				const char *pin);
 int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm);
 int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm,
 				  const char *pin);
+int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+					   const char *pin);
 int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
 				const char *pin);
 void snd_soc_dapm_auto_nc_codec_pins(struct snd_soc_codec *codec);
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index ae5a171..4483fad 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -12,6 +12,7 @@
 	int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
 	int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
 	void (*iscsit_free_np)(struct iscsi_np *);
+	void (*iscsit_wait_conn)(struct iscsi_conn *);
 	void (*iscsit_free_conn)(struct iscsi_conn *);
 	int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
 	int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32);
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ddc179b..1fef3e6 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -83,7 +83,7 @@
 		),
 
 	TP_fast_assign(
-		__entry->client_id = clnt->cl_clid;
+		__entry->client_id = clnt ? clnt->cl_clid : -1;
 		__entry->task_id = task->tk_pid;
 		__entry->action = action;
 		__entry->runstate = task->tk_runstate;
@@ -91,7 +91,7 @@
 		__entry->flags = task->tk_flags;
 		),
 
-	TP_printk("task:%u@%u flags=%4.4x state=%4.4lx status=%d action=%pf",
+	TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d action=%pf",
 		__entry->task_id, __entry->client_id,
 		__entry->flags,
 		__entry->runstate,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index c7bbbe7..464ea82 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -287,11 +287,11 @@
 		__field(int,		reason)
 	),
 	TP_fast_assign(
-		unsigned long older_than_this = work->older_than_this;
+		unsigned long *older_than_this = work->older_than_this;
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__entry->older	= older_than_this;
+		__entry->older	= older_than_this ?  *older_than_this : 0;
 		__entry->age	= older_than_this ?
-				  (jiffies - older_than_this) * 1000 / HZ : -1;
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
 	),
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a20a9b4..dde8041 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -692,9 +692,13 @@
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 273
 __SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
 
 #undef __NR_syscalls
-#define __NR_syscalls 274
+#define __NR_syscalls 276
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 1cf18b4..aefa2f6 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -510,6 +510,7 @@
 #define DRM_RADEON_GEM_GET_TILING	0x29
 #define DRM_RADEON_GEM_BUSY		0x2a
 #define DRM_RADEON_GEM_VA		0x2b
+#define DRM_RADEON_GEM_OP		0x2c
 
 #define DRM_IOCTL_RADEON_CP_INIT    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_INIT, drm_radeon_init_t)
 #define DRM_IOCTL_RADEON_CP_START   DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_START)
@@ -552,6 +553,7 @@
 #define DRM_IOCTL_RADEON_GEM_GET_TILING	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_GET_TILING, struct drm_radeon_gem_get_tiling)
 #define DRM_IOCTL_RADEON_GEM_BUSY	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_BUSY, struct drm_radeon_gem_busy)
 #define DRM_IOCTL_RADEON_GEM_VA		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_VA, struct drm_radeon_gem_va)
+#define DRM_IOCTL_RADEON_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_OP, struct drm_radeon_gem_op)
 
 typedef struct drm_radeon_init {
 	enum {
@@ -884,6 +886,16 @@
 	uint64_t data_ptr;
 };
 
+/* Sets or returns a value associated with a buffer. */
+struct drm_radeon_gem_op {
+	uint32_t	handle; /* buffer */
+	uint32_t	op;     /* RADEON_GEM_OP_* */
+	uint64_t	value;  /* input or return value */
+};
+
+#define RADEON_GEM_OP_GET_INITIAL_DOMAIN	0
+#define RADEON_GEM_OP_SET_INITIAL_DOMAIN	1
+
 #define RADEON_VA_MAP			1
 #define RADEON_VA_UNMAP			2
 
@@ -992,6 +1004,9 @@
 #define RADEON_INFO_VCE_FW_VERSION	0x1b
 /* version of VCE feedback */
 #define RADEON_INFO_VCE_FB_VERSION	0x1c
+#define RADEON_INFO_NUM_BYTES_MOVED	0x1d
+#define RADEON_INFO_VRAM_USAGE		0x1e
+#define RADEON_INFO_GTT_USAGE		0x1f
 
 
 struct drm_radeon_info {
diff --git a/init/main.c b/init/main.c
index eb03090..9c7fd4c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -561,7 +561,6 @@
 	init_timers();
 	hrtimers_init();
 	softirq_init();
-	acpi_early_init();
 	timekeeping_init();
 	time_init();
 	sched_clock_postinit();
@@ -613,6 +612,7 @@
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();
+	acpi_early_init();
 #ifdef CONFIG_X86
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 383d638..5bb8bfe 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -22,6 +22,16 @@
 	return which;
 }
 
+static int proc_mq_dointvec(ctl_table *table, int write,
+			    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table mq_table;
+	memcpy(&mq_table, table, sizeof(mq_table));
+	mq_table.data = get_mq(table);
+
+	return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
 static int proc_mq_dointvec_minmax(ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -33,12 +43,10 @@
 					lenp, ppos);
 }
 #else
+#define proc_mq_dointvec NULL
 #define proc_mq_dointvec_minmax NULL
 #endif
 
-static int msg_queues_limit_min = MIN_QUEUESMAX;
-static int msg_queues_limit_max = HARD_QUEUESMAX;
-
 static int msg_max_limit_min = MIN_MSGMAX;
 static int msg_max_limit_max = HARD_MSGMAX;
 
@@ -51,9 +59,7 @@
 		.data		= &init_ipc_ns.mq_queues_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
-		.extra1		= &msg_queues_limit_min,
-		.extra2		= &msg_queues_limit_max,
+		.proc_handler	= proc_mq_dointvec,
 	},
 	{
 		.procname	= "msg_max",
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index ccf1f9f..c3b3117 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -433,9 +433,9 @@
 		error = -EACCES;
 		goto out_unlock;
 	}
-	if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
-	    (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
-	     !capable(CAP_SYS_RESOURCE))) {
+
+	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+	    !capable(CAP_SYS_RESOURCE)) {
 		error = -ENOSPC;
 		goto out_unlock;
 	}
diff --git a/ipc/msg.c b/ipc/msg.c
index 245db11..6498531 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -901,6 +901,8 @@
 		return -EINVAL;
 
 	if (msgflg & MSG_COPY) {
+		if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+			return -EINVAL;
 		copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
 		if (IS_ERR(copy))
 			return PTR_ERR(copy);
diff --git a/kernel/audit.c b/kernel/audit.c
index 34c5a23..3392d3e 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -182,7 +182,7 @@
 
 struct audit_reply {
 	__u32 portid;
-	pid_t pid;
+	struct net *net;	
 	struct sk_buff *skb;
 };
 
@@ -500,7 +500,7 @@
 {
 	struct audit_netlink_list *dest = _dest;
 	struct sk_buff *skb;
-	struct net *net = get_net_ns_by_pid(dest->pid);
+	struct net *net = dest->net;
 	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	/* wait for parent to finish and send an ACK */
@@ -510,6 +510,7 @@
 	while ((skb = __skb_dequeue(&dest->q)) != NULL)
 		netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
 
+	put_net(net);
 	kfree(dest);
 
 	return 0;
@@ -543,7 +544,7 @@
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
-	struct net *net = get_net_ns_by_pid(reply->pid);
+	struct net *net = reply->net;
 	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	mutex_lock(&audit_cmd_mutex);
@@ -552,12 +553,13 @@
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
 	netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
+	put_net(net);
 	kfree(reply);
 	return 0;
 }
 /**
  * audit_send_reply - send an audit reply message via netlink
- * @portid: netlink port to which to send reply
+ * @request_skb: skb of request we are replying to (used to target the reply)
  * @seq: sequence number
  * @type: audit message type
  * @done: done (last) flag
@@ -568,9 +570,11 @@
  * Allocates an skb, builds the netlink message, and sends it to the port id.
  * No failure notifications.
  */
-static void audit_send_reply(__u32 portid, int seq, int type, int done,
+static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
 			     int multi, const void *payload, int size)
 {
+	u32 portid = NETLINK_CB(request_skb).portid;
+	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct sk_buff *skb;
 	struct task_struct *tsk;
 	struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
@@ -583,8 +587,8 @@
 	if (!skb)
 		goto out;
 
+	reply->net = get_net(net);
 	reply->portid = portid;
-	reply->pid = task_pid_vnr(current);
 	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
@@ -673,8 +677,7 @@
 
 	seq = nlmsg_hdr(skb)->nlmsg_seq;
 
-	audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-			 &af, sizeof(af));
+	audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
 
 	return 0;
 }
@@ -794,8 +797,7 @@
 		s.backlog		= skb_queue_len(&audit_skb_queue);
 		s.version		= AUDIT_VERSION_LATEST;
 		s.backlog_wait_time	= audit_backlog_wait_time;
-		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-				 &s, sizeof(s));
+		audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_SET: {
@@ -905,7 +907,7 @@
 					   seq, data, nlmsg_len(nlh));
 		break;
 	case AUDIT_LIST_RULES:
-		err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+		err = audit_list_rules_send(skb, seq);
 		break;
 	case AUDIT_TRIM:
 		audit_trim_trees();
@@ -970,8 +972,8 @@
 			memcpy(sig_data->ctx, ctx, len);
 			security_release_secctx(ctx, len);
 		}
-		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO,
-				0, 0, sig_data, sizeof(*sig_data) + len);
+		audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
+				 sig_data, sizeof(*sig_data) + len);
 		kfree(sig_data);
 		break;
 	case AUDIT_TTY_GET: {
@@ -983,8 +985,7 @@
 		s.log_passwd = tsk->signal->audit_tty_log_passwd;
 		spin_unlock(&tsk->sighand->siglock);
 
-		audit_send_reply(NETLINK_CB(skb).portid, seq,
-				 AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
+		audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_TTY_SET: {
diff --git a/kernel/audit.h b/kernel/audit.h
index 57cc64d..8df13221 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -247,7 +247,7 @@
 
 struct audit_netlink_list {
 	__u32 portid;
-	pid_t pid;
+	struct net *net;
 	struct sk_buff_head q;
 };
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 67ccf0e..135944a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -916,7 +916,7 @@
 				   struct fsnotify_mark *inode_mark,
 				   struct fsnotify_mark *vfsmount_mark,
 				   u32 mask, void *data, int data_type,
-				   const unsigned char *file_name)
+				   const unsigned char *file_name, u32 cookie)
 {
 	return 0;
 }
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 2596fac..70b4554 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -471,7 +471,7 @@
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
 				    u32 mask, void *data, int data_type,
-				    const unsigned char *dname)
+				    const unsigned char *dname, u32 cookie)
 {
 	struct inode *inode;
 	struct audit_parent *parent;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 14a78cc..92062fd 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -29,6 +29,8 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/security.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
 #include "audit.h"
 
 /*
@@ -1065,11 +1067,13 @@
 
 /**
  * audit_list_rules_send - list the audit rules
- * @portid: target portid for netlink audit messages
+ * @request_skb: skb of request we are replying to (used to target the reply)
  * @seq: netlink audit message sequence (serial) number
  */
-int audit_list_rules_send(__u32 portid, int seq)
+int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 {
+	u32 portid = NETLINK_CB(request_skb).portid;
+	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct task_struct *tsk;
 	struct audit_netlink_list *dest;
 	int err = 0;
@@ -1083,8 +1087,8 @@
 	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
+	dest->net = get_net(net);
 	dest->portid = portid;
-	dest->pid = task_pid_vnr(current);
 	skb_queue_head_init(&dest->q);
 
 	mutex_lock(&audit_filter_mutex);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4410ac6..e6b1b66 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -974,12 +974,6 @@
  *    Temporarilly set tasks mems_allowed to target nodes of migration,
  *    so that the migration code can allocate pages on these nodes.
  *
- *    Call holding cpuset_mutex, so current's cpuset won't change
- *    during this call, as manage_mutex holds off any cpuset_attach()
- *    calls.  Therefore we don't need to take task_lock around the
- *    call to guarantee_online_mems(), as we know no one is changing
- *    our task's cpuset.
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -996,8 +990,10 @@
 
 	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
 
+	rcu_read_lock();
 	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
 	guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+	rcu_read_unlock();
 }
 
 /*
@@ -2486,9 +2482,9 @@
 
 	task_lock(current);
 	cs = nearest_hardwall_ancestor(task_cs(current));
+	allowed = node_isset(node, cs->mems_allowed);
 	task_unlock(current);
 
-	allowed = node_isset(node, cs->mems_allowed);
 	mutex_unlock(&callback_mutex);
 	return allowed;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6..fa0b2d4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7856,14 +7856,14 @@
 static void __perf_event_exit_context(void *__info)
 {
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
+	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
-		__perf_remove_from_context(event);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7887,11 +7887,11 @@
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf68bb3..f140337 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -10,6 +10,7 @@
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_irq.h>
 #include <linux/topology.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 481a13c..d3bf660 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -802,8 +802,7 @@
 
 static void wake_threads_waitq(struct irq_desc *desc)
 {
-	if (atomic_dec_and_test(&desc->threads_active) &&
-	    waitqueue_active(&desc->wait_for_threads))
+	if (atomic_dec_and_test(&desc->threads_active))
 		wake_up(&desc->wait_for_threads);
 }
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 6631e1e..ebdd9c1 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -549,14 +549,14 @@
 		struct page *page;
 
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
 		per_cpu(cpu_profile_hits, cpu)[1]
 				= (struct profile_hit *)page_address(page);
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 43c2bcc..b30a292 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -301,14 +301,14 @@
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
-	preempt_disable();
+	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return clock;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6edbef2..f5c6635 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3338,6 +3338,15 @@
 				return -EPERM;
 		}
 
+		 /*
+		  * Can't set/change SCHED_DEADLINE policy at all for now
+		  * (safest behavior); in the future we would like to allow
+		  * unprivileged DL tasks to increase their relative deadline
+		  * or reduce their runtime (both ways reducing utilization)
+		  */
+		if (dl_policy(policy))
+			return -EPERM;
+
 		/*
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b8838b..5b9bb42 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
-	WARN_ON(!cpu_present(idx) || idx == IDX_INVALID);
+	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
 
 	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
 		cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@
 	}
 
 out:
-	WARN_ON(!cpu_present(best_cpu) && best_cpu != -1);
+	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
 	return best_cpu;
 }
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 15cbc17..6e79b3f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -135,7 +135,6 @@
 static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory++;
@@ -146,7 +145,6 @@
 static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory--;
@@ -564,6 +562,8 @@
 	return 1;
 }
 
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
@@ -627,11 +627,13 @@
 		struct rt_rq *rt_rq = &rq->rt;
 
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_time += delta_exec;
 		/*
 		 * We'll let actual RT tasks worry about the overflow here, we
-		 * have our own CBS to keep us inline -- see above.
+		 * have our own CBS to keep us inline; only account when RT
+		 * bandwidth is relevant.
 		 */
+		if (sched_rt_bandwidth_account(rt_rq))
+			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7815709..9b4c4f3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7001,15 +7001,15 @@
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/*
-	 * Ensure the task's vruntime is normalized, so that when its
+	 * Ensure the task's vruntime is normalized, so that when it's
 	 * switched back to the fair class the enqueue_entity(.flags=0) will
 	 * do the right thing.
 	 *
-	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * If it's on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it's !on_rq, then only when
 	 * the task is sleeping will it still have non-normalized vruntime.
 	 */
-	if (!se->on_rq && p->state != TASK_RUNNING) {
+	if (!p->on_rq && p->state != TASK_RUNNING) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b7..1999021 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -538,6 +538,14 @@
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+	return (hrtimer_active(&rt_b->rt_period_timer) ||
+		rt_rq->rt_time < rt_b->rt_runtime);
+}
+
 #ifdef CONFIG_SMP
 /*
  * We ran out of runtime, see if we can borrow some from our neighbours.
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 84571e0..01fbae5 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -293,7 +293,7 @@
 	 */
 	smp_call_function_single(min(cpu1, cpu2),
 				 &irq_cpu_stop_queue_work,
-				 &call_args, 0);
+				 &call_args, 1);
 	lg_local_unlock(&stop_cpus_lock);
 	preempt_enable();
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4..f3989ce 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1777,6 +1777,16 @@
 {
 	struct ftrace_event_call **call, **start, **end;
 
+	if (!mod->num_trace_events)
+		return;
+
+	/* Don't add infrastructure for mods without tracepoints */
+	if (trace_module_has_bad_taint(mod)) {
+		pr_err("%s: module has bad taint, not creating trace events\n",
+		       mod->name);
+		return;
+	}
+
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f2654..031cc56 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,6 +631,11 @@
 EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 
 #ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
 static int tracepoint_module_coming(struct module *mod)
 {
 	struct tp_module *tp_mod, *iter;
@@ -641,7 +646,7 @@
 	 * module headers (for forced load), to make sure we don't cause a crash.
 	 * Staging and out-of-tree GPL modules are fine.
 	 */
-	if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+	if (trace_module_has_bad_taint(mod))
 		return 0;
 	mutex_lock(&tracepoints_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 2defd13..98f2d7e 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -424,111 +424,134 @@
 EXPORT_SYMBOL(debug_dma_dump_mappings);
 
 /*
- * For each page mapped (initial page in the case of
- * dma_alloc_coherent/dma_map_{single|page}, or each page in a
- * scatterlist) insert into this tree using the pfn as the key. At
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
  * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry.  If
- * the pfn already exists at insertion time add a tag as a reference
+ * the entry already exists at insertion time add a tag as a reference
  * count for the overlapping mappings.  For now, the overlap tracking
- * just ensures that 'unmaps' balance 'maps' before marking the pfn
- * idle, but we should also be flagging overlaps as an API violation.
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
  *
  * Memory usage is mostly constrained by the maximum number of available
  * dma-debug entries in that we need a free dma_debug_entry before
- * inserting into the tree.  In the case of dma_map_{single|page} and
- * dma_alloc_coherent there is only one dma_debug_entry and one pfn to
- * track per event.  dma_map_sg(), on the other hand,
- * consumes a single dma_debug_entry, but inserts 'nents' entries into
- * the tree.
+ * inserting into the tree.  In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
  *
  * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if the given page is in the active set.
+ * warning if any cachelines in the given page are in the active set.
  */
-static RADIX_TREE(dma_active_pfn, GFP_NOWAIT);
+static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
 static DEFINE_SPINLOCK(radix_lock);
-#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
 
-static int active_pfn_read_overlap(unsigned long pfn)
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+	return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+		(entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
 {
 	int overlap = 0, i;
 
 	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
-		if (radix_tree_tag_get(&dma_active_pfn, pfn, i))
+		if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
 			overlap |= 1 << i;
 	return overlap;
 }
 
-static int active_pfn_set_overlap(unsigned long pfn, int overlap)
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
 {
 	int i;
 
-	if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0)
+	if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
 		return overlap;
 
 	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
 		if (overlap & 1 << i)
-			radix_tree_tag_set(&dma_active_pfn, pfn, i);
+			radix_tree_tag_set(&dma_active_cacheline, cln, i);
 		else
-			radix_tree_tag_clear(&dma_active_pfn, pfn, i);
+			radix_tree_tag_clear(&dma_active_cacheline, cln, i);
 
 	return overlap;
 }
 
-static void active_pfn_inc_overlap(unsigned long pfn)
+static void active_cacheline_inc_overlap(phys_addr_t cln)
 {
-	int overlap = active_pfn_read_overlap(pfn);
+	int overlap = active_cacheline_read_overlap(cln);
 
-	overlap = active_pfn_set_overlap(pfn, ++overlap);
+	overlap = active_cacheline_set_overlap(cln, ++overlap);
 
 	/* If we overflowed the overlap counter then we're potentially
 	 * leaking dma-mappings.  Otherwise, if maps and unmaps are
 	 * balanced then this overflow may cause false negatives in
-	 * debug_dma_assert_idle() as the pfn may be marked idle
+	 * debug_dma_assert_idle() as the cacheline may be marked idle
 	 * prematurely.
 	 */
-	WARN_ONCE(overlap > ACTIVE_PFN_MAX_OVERLAP,
-		  "DMA-API: exceeded %d overlapping mappings of pfn %lx\n",
-		  ACTIVE_PFN_MAX_OVERLAP, pfn);
+	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+		  "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
 
-static int active_pfn_dec_overlap(unsigned long pfn)
+static int active_cacheline_dec_overlap(phys_addr_t cln)
 {
-	int overlap = active_pfn_read_overlap(pfn);
+	int overlap = active_cacheline_read_overlap(cln);
 
-	return active_pfn_set_overlap(pfn, --overlap);
+	return active_cacheline_set_overlap(cln, --overlap);
 }
 
-static int active_pfn_insert(struct dma_debug_entry *entry)
+static int active_cacheline_insert(struct dma_debug_entry *entry)
 {
+	phys_addr_t cln = to_cacheline_number(entry);
 	unsigned long flags;
 	int rc;
 
+	/* If the device is not writing memory then we don't have any
+	 * concerns about the cpu consuming stale data.  This mitigates
+	 * legitimate usages of overlapping mappings.
+	 */
+	if (entry->direction == DMA_TO_DEVICE)
+		return 0;
+
 	spin_lock_irqsave(&radix_lock, flags);
-	rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry);
+	rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
 	if (rc == -EEXIST)
-		active_pfn_inc_overlap(entry->pfn);
+		active_cacheline_inc_overlap(cln);
 	spin_unlock_irqrestore(&radix_lock, flags);
 
 	return rc;
 }
 
-static void active_pfn_remove(struct dma_debug_entry *entry)
+static void active_cacheline_remove(struct dma_debug_entry *entry)
 {
+	phys_addr_t cln = to_cacheline_number(entry);
 	unsigned long flags;
 
+	/* ...mirror the insert case */
+	if (entry->direction == DMA_TO_DEVICE)
+		return;
+
 	spin_lock_irqsave(&radix_lock, flags);
 	/* since we are counting overlaps the final put of the
-	 * entry->pfn will occur when the overlap count is 0.
-	 * active_pfn_dec_overlap() returns -1 in that case
+	 * cacheline will occur when the overlap count is 0.
+	 * active_cacheline_dec_overlap() returns -1 in that case
 	 */
-	if (active_pfn_dec_overlap(entry->pfn) < 0)
-		radix_tree_delete(&dma_active_pfn, entry->pfn);
+	if (active_cacheline_dec_overlap(cln) < 0)
+		radix_tree_delete(&dma_active_cacheline, cln);
 	spin_unlock_irqrestore(&radix_lock, flags);
 }
 
 /**
  * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_pfn tree
+ * @page: page to lookup in the dma_active_cacheline tree
  *
  * Place a call to this routine in cases where the cpu touching the page
  * before the dma completes (page is dma_unmapped) will lead to data
@@ -536,22 +559,38 @@
  */
 void debug_dma_assert_idle(struct page *page)
 {
+	static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
+	struct dma_debug_entry *entry = NULL;
+	void **results = (void **) &ents;
+	unsigned int nents, i;
 	unsigned long flags;
-	struct dma_debug_entry *entry;
+	phys_addr_t cln;
 
 	if (!page)
 		return;
 
+	cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
 	spin_lock_irqsave(&radix_lock, flags);
-	entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page));
+	nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
+				       CACHELINES_PER_PAGE);
+	for (i = 0; i < nents; i++) {
+		phys_addr_t ent_cln = to_cacheline_number(ents[i]);
+
+		if (ent_cln == cln) {
+			entry = ents[i];
+			break;
+		} else if (ent_cln >= cln + CACHELINES_PER_PAGE)
+			break;
+	}
 	spin_unlock_irqrestore(&radix_lock, flags);
 
 	if (!entry)
 		return;
 
+	cln = to_cacheline_number(entry);
 	err_printk(entry->dev, entry,
-		   "DMA-API: cpu touching an active dma mapped page "
-		   "[pfn=0x%lx]\n", entry->pfn);
+		   "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+		   &cln);
 }
 
 /*
@@ -568,9 +607,9 @@
 	hash_bucket_add(bucket, entry);
 	put_hash_bucket(bucket, &flags);
 
-	rc = active_pfn_insert(entry);
+	rc = active_cacheline_insert(entry);
 	if (rc == -ENOMEM) {
-		pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n");
+		pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
 		global_disable = true;
 	}
 
@@ -631,7 +670,7 @@
 {
 	unsigned long flags;
 
-	active_pfn_remove(entry);
+	active_cacheline_remove(entry);
 
 	/*
 	 * add to beginning of the list - this way the entries are
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7811ed3..bd4a8df 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1253,8 +1253,10 @@
 
 		node = indirect_to_ptr(node);
 		max_index = radix_tree_maxindex(node->height);
-		if (cur_index > max_index)
+		if (cur_index > max_index) {
+			rcu_read_unlock();
 			break;
+		}
 
 		cur_index = __locate(node, item, cur_index, &found_index);
 		rcu_read_unlock();
diff --git a/mm/Kconfig b/mm/Kconfig
index 2d9f150..2888024 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -575,5 +575,5 @@
 	  then you should select this. This causes zsmalloc to use page table
 	  mapping rather than copying for object mapping.
 
-	  You can check speed with zsmalloc benchmark[1].
-	  [1] https://github.com/spartacus06/zsmalloc
+	  You can check speed with zsmalloc benchmark:
+	  https://github.com/spartacus06/zsmapbench
diff --git a/mm/compaction.c b/mm/compaction.c
index b48c525..9185775 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -251,7 +251,6 @@
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long nr_strict_required = end_pfn - blockpfn;
 	unsigned long flags;
 	bool locked = false;
 
@@ -264,11 +263,12 @@
 
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
-			continue;
+			goto isolate_fail;
+
 		if (!valid_page)
 			valid_page = page;
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/*
 		 * The zone lock must be held to isolate freepages.
@@ -289,12 +289,10 @@
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		if (!isolated && strict)
-			break;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
@@ -305,7 +303,15 @@
 		if (isolated) {
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
+			continue;
 		}
+
+isolate_fail:
+		if (strict)
+			break;
+		else
+			continue;
+
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -315,7 +321,7 @@
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required > total_isolated)
+	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
 	if (locked)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da23eb9..1546655 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,8 +1166,10 @@
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
-			if (ret & VM_FAULT_OOM)
+			if (ret & VM_FAULT_OOM) {
 				split_huge_page(page);
+				ret |= VM_FAULT_FALLBACK;
+			}
 			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
@@ -1179,9 +1181,10 @@
 		if (page) {
 			split_huge_page(page);
 			put_page(page);
-		}
+		} else
+			split_huge_page_pmd(vma, address, pmd);
+		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
-		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
@@ -1958,7 +1961,7 @@
 	return ret;
 }
 
-#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE)
+#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
 
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)
diff --git a/mm/ksm.c b/mm/ksm.c
index aa4c7c7..68710e8 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -444,7 +444,7 @@
 static struct page *page_trans_compound_anon(struct page *page)
 {
 	if (PageTransCompound(page)) {
-		struct page *head = compound_trans_head(page);
+		struct page *head = compound_head(page);
 		/*
 		 * head may actually be splitted and freed from under
 		 * us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd..5b6b003 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1127,8 +1127,8 @@
 	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		if ((next_css->flags & CSS_ONLINE) &&
-				(next_css == &root->css || css_tryget(next_css)))
+		if ((next_css == &root->css) ||
+		    ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
 			return mem_cgroup_from_css(next_css);
 
 		prev_css = next_css;
@@ -1687,7 +1687,7 @@
 	 * protects memcg_name and makes sure that parallel ooms do not
 	 * interleave
 	 */
-	static DEFINE_SPINLOCK(oom_info_lock);
+	static DEFINE_MUTEX(oom_info_lock);
 	struct cgroup *task_cgrp;
 	struct cgroup *mem_cgrp;
 	static char memcg_name[PATH_MAX];
@@ -1698,7 +1698,7 @@
 	if (!p)
 		return;
 
-	spin_lock(&oom_info_lock);
+	mutex_lock(&oom_info_lock);
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1767,7 +1767,7 @@
 
 		pr_cont("\n");
 	}
-	spin_unlock(&oom_info_lock);
+	mutex_unlock(&oom_info_lock);
 }
 
 /*
@@ -6595,6 +6595,7 @@
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event, *tmp;
+	struct cgroup_subsys_state *iter;
 
 	/*
 	 * Unregister events and notify userspace.
@@ -6611,7 +6612,14 @@
 	kmem_cgroup_css_offline(memcg);
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
-	mem_cgroup_reparent_charges(memcg);
+
+	/*
+	 * This requires that offlining is serialized.  Right now that is
+	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+	 */
+	css_for_each_descendant_post(iter, css)
+		mem_cgroup_reparent_charges(mem_cgroup_from_css(iter));
+
 	mem_cgroup_destroy_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2f2f34a..90002ea 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1651,7 +1651,7 @@
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_trans_head(page);
+	struct page *hpage = compound_head(page);
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
diff --git a/mm/memory.c b/mm/memory.c
index be6a0c0..22dfa61 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3348,6 +3348,7 @@
 		if (ret & VM_FAULT_LOCKED)
 			unlock_page(vmf.page);
 		ret = VM_FAULT_HWPOISON;
+		page_cache_release(vmf.page);
 		goto uncharge_out;
 	}
 
@@ -3703,7 +3704,6 @@
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
-retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3741,20 +3741,13 @@
 			if (dirty && !pmd_write(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
-				/*
-				 * If COW results in an oom, the huge pmd will
-				 * have been split, so retry the fault on the
-				 * pte for a smaller charge.
-				 */
-				if (unlikely(ret & VM_FAULT_OOM))
-					goto retry;
-				return ret;
+				if (!(ret & VM_FAULT_FALLBACK))
+					return ret;
 			} else {
 				huge_pmd_set_accessed(mm, vma, address, pmd,
 						      orig_pmd, dirty);
+				return 0;
 			}
-
-			return 0;
 		}
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 482a33d..b494fdb 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1158,7 +1158,7 @@
 					pm->node);
 	else
 		return alloc_pages_exact_node(pm->node,
-				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
 /*
@@ -1544,9 +1544,9 @@
 	struct page *newpage;
 
 	newpage = alloc_pages_exact_node(nid,
-					 (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
-					  __GFP_NOMEMALLOC | __GFP_NORETRY |
-					  __GFP_NOWARN) &
+					 (GFP_HIGHUSER_MOVABLE |
+					  __GFP_THISNODE | __GFP_NOMEMALLOC |
+					  __GFP_NORETRY | __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 
 	return newpage;
@@ -1747,7 +1747,8 @@
 		goto out_dropref;
 
 	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3758a0..3bac76a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -369,9 +369,11 @@
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
-		__SetPageTail(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
@@ -1236,6 +1238,15 @@
 	}
 	local_irq_restore(flags);
 }
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
+}
+#else
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return false;
+}
 #endif
 
 /*
@@ -1572,7 +1583,13 @@
 					  get_pageblock_migratetype(page));
 	}
 
-	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	/*
+	 * NOTE: GFP_THISNODE allocations do not partake in the kswapd
+	 * aging protocol, so they can't be fair.
+	 */
+	if (!gfp_thisnode_allocation(gfp_flags))
+		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
@@ -1944,8 +1961,12 @@
 		 * ultimately fall back to remote zones that do not
 		 * partake in the fairness round-robin cycle of this
 		 * zonelist.
+		 *
+		 * NOTE: GFP_THISNODE allocations do not partake in
+		 * the kswapd aging protocol, so they can't be fair.
 		 */
-		if (alloc_flags & ALLOC_WMARK_LOW) {
+		if ((alloc_flags & ALLOC_WMARK_LOW) &&
+		    !gfp_thisnode_allocation(gfp_mask)) {
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
 			if (!zone_local(preferred_zone, zone))
@@ -2501,8 +2522,7 @@
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (IS_ENABLED(CONFIG_NUMA) &&
-			(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+	if (gfp_thisnode_allocation(gfp_mask))
 		goto nopage;
 
 restart:
diff --git a/mm/swap.c b/mm/swap.c
index b31ba67..0092097 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -98,7 +98,7 @@
 	}
 
 	/* __split_huge_page_refcount can run under us */
-	page_head = compound_trans_head(page);
+	page_head = compound_head(page);
 
 	/*
 	 * THP can not break up slab pages so avoid taking
@@ -253,7 +253,7 @@
 	 */
 	unsigned long flags;
 	bool got;
-	struct page *page_head = compound_trans_head(page);
+	struct page *page_head = compound_head(page);
 
 	/* Ref to put_compound_page() comment. */
 	if (!__compound_tail_refcounted(page_head)) {
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index de51c48..4b65aa4 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -538,6 +538,9 @@
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
 	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
 }
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ef66365..93067ec 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1127,9 +1127,10 @@
 					struct net_bridge_port *port,
 					struct bridge_mcast_querier *querier,
 					int saddr,
+					bool is_general_query,
 					unsigned long max_delay)
 {
-	if (saddr)
+	if (saddr && is_general_query)
 		br_multicast_update_querier_timer(br, querier, max_delay);
 	else if (timer_pending(&querier->timer))
 		return;
@@ -1181,8 +1182,16 @@
 			    IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
 	}
 
+	/* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer
+	 * all-systems destination addresses (224.0.0.1) for general queries
+	 */
+	if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr,
-				    max_delay);
+				    !group, max_delay);
 
 	if (!group)
 		goto out;
@@ -1228,6 +1237,7 @@
 	unsigned long max_delay;
 	unsigned long now = jiffies;
 	const struct in6_addr *group = NULL;
+	bool is_general_query;
 	int err = 0;
 
 	spin_lock(&br->multicast_lock);
@@ -1235,6 +1245,12 @@
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;
@@ -1256,8 +1272,19 @@
 		max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL);
 	}
 
+	is_general_query = group && ipv6_addr_any(group);
+
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
+	 * all-nodes destination address (ff02::1) for general queries
+	 */
+	if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	br_multicast_query_received(br, port, &br->ip6_querier,
-				    !ipv6_addr_any(&ip6h->saddr), max_delay);
+				    !ipv6_addr_any(&ip6h->saddr),
+				    is_general_query, max_delay);
 
 	if (!group)
 		goto out;
diff --git a/net/can/raw.c b/net/can/raw.c
index 8be757c..081e81f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -121,13 +121,9 @@
 	if (!ro->recv_own_msgs && oskb->sk == sk)
 		return;
 
-	/* do not pass frames with DLC > 8 to a legacy socket */
-	if (!ro->fd_frames) {
-		struct canfd_frame *cfd = (struct canfd_frame *)oskb->data;
-
-		if (unlikely(cfd->len > CAN_MAX_DLEN))
-			return;
-	}
+	/* do not pass non-CAN2.0 frames to a legacy socket */
+	if (!ro->fd_frames && oskb->len != CAN_MTU)
+		return;
 
 	/* clone the given skb to be able to enqueue it into the rcv queue */
 	skb = skb_clone(oskb, GFP_ATOMIC);
@@ -738,9 +734,7 @@
 		       struct msghdr *msg, size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct raw_sock *ro = raw_sk(sk);
 	struct sk_buff *skb;
-	int rxmtu;
 	int err = 0;
 	int noblock;
 
@@ -751,20 +745,10 @@
 	if (!skb)
 		return err;
 
-	/*
-	 * when serving a legacy socket the DLC <= 8 is already checked inside
-	 * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy
-	 * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU
-	 */
-	if (!ro->fd_frames)
-		rxmtu = CAN_MTU;
-	else
-		rxmtu = skb->len;
-
-	if (size < rxmtu)
+	if (size < skb->len)
 		msg->msg_flags |= MSG_TRUNC;
 	else
-		size = rxmtu;
+		size = skb->len;
 
 	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
 	if (err < 0) {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index b9e9e0d..e161290 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -766,9 +766,6 @@
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
 
-	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
-		goto out;
-
 	/*
 	 *	periodically recompute ReachableTime from random function
 	 */
@@ -781,6 +778,9 @@
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 	}
 
+	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+		goto out;
+
 	for (i = 0 ; i < (1 << nht->hash_shift); i++) {
 		np = &nht->hash_buckets[i];
 
@@ -3046,7 +3046,7 @@
 	if (!t)
 		goto err;
 
-	for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) {
+	for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) {
 		t->neigh_vars[i].data += (long) p;
 		t->neigh_vars[i].extra1 = dev;
 		t->neigh_vars[i].extra2 = p;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5976ef0..869c7af 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -707,9 +707,6 @@
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
 	__nf_copy(new, old);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	new->nf_trace		= old->nf_trace;
-#endif
 #ifdef CONFIG_NET_SCHED
 	new->tc_index		= old->tc_index;
 #ifdef CONFIG_NET_CLS_ACT
@@ -2841,81 +2838,84 @@
 
 /**
  *	skb_segment - Perform protocol segmentation on skb.
- *	@skb: buffer to segment
+ *	@head_skb: buffer to segment
  *	@features: features for the output path (see dev->features)
  *
  *	This function performs segmentation on the given skb.  It returns
  *	a pointer to the first in a list of new skbs for the segments.
  *	In case of error it returns ERR_PTR(err).
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
+struct sk_buff *skb_segment(struct sk_buff *head_skb,
+			    netdev_features_t features)
 {
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
-	skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
-	unsigned int mss = skb_shinfo(skb)->gso_size;
-	unsigned int doffset = skb->data - skb_mac_header(skb);
+	struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
+	skb_frag_t *frag = skb_shinfo(head_skb)->frags;
+	unsigned int mss = skb_shinfo(head_skb)->gso_size;
+	unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
+	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
-	unsigned int tnl_hlen = skb_tnl_header_len(skb);
+	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
 	unsigned int headroom;
 	unsigned int len;
 	__be16 proto;
 	bool csum;
 	int sg = !!(features & NETIF_F_SG);
-	int nfrags = skb_shinfo(skb)->nr_frags;
+	int nfrags = skb_shinfo(head_skb)->nr_frags;
 	int err = -ENOMEM;
 	int i = 0;
 	int pos;
 
-	proto = skb_network_protocol(skb);
+	proto = skb_network_protocol(head_skb);
 	if (unlikely(!proto))
 		return ERR_PTR(-EINVAL);
 
 	csum = !!can_checksum_protocol(features, proto);
-	__skb_push(skb, doffset);
-	headroom = skb_headroom(skb);
-	pos = skb_headlen(skb);
+	__skb_push(head_skb, doffset);
+	headroom = skb_headroom(head_skb);
+	pos = skb_headlen(head_skb);
 
 	do {
 		struct sk_buff *nskb;
-		skb_frag_t *frag;
+		skb_frag_t *nskb_frag;
 		int hsize;
 		int size;
 
-		len = skb->len - offset;
+		len = head_skb->len - offset;
 		if (len > mss)
 			len = mss;
 
-		hsize = skb_headlen(skb) - offset;
+		hsize = skb_headlen(head_skb) - offset;
 		if (hsize < 0)
 			hsize = 0;
 		if (hsize > len || !sg)
 			hsize = len;
 
-		if (!hsize && i >= nfrags && skb_headlen(fskb) &&
-		    (skb_headlen(fskb) == len || sg)) {
-			BUG_ON(skb_headlen(fskb) > len);
+		if (!hsize && i >= nfrags && skb_headlen(list_skb) &&
+		    (skb_headlen(list_skb) == len || sg)) {
+			BUG_ON(skb_headlen(list_skb) > len);
 
 			i = 0;
-			nfrags = skb_shinfo(fskb)->nr_frags;
-			skb_frag = skb_shinfo(fskb)->frags;
-			pos += skb_headlen(fskb);
+			nfrags = skb_shinfo(list_skb)->nr_frags;
+			frag = skb_shinfo(list_skb)->frags;
+			frag_skb = list_skb;
+			pos += skb_headlen(list_skb);
 
 			while (pos < offset + len) {
 				BUG_ON(i >= nfrags);
 
-				size = skb_frag_size(skb_frag);
+				size = skb_frag_size(frag);
 				if (pos + size > offset + len)
 					break;
 
 				i++;
 				pos += size;
-				skb_frag++;
+				frag++;
 			}
 
-			nskb = skb_clone(fskb, GFP_ATOMIC);
-			fskb = fskb->next;
+			nskb = skb_clone(list_skb, GFP_ATOMIC);
+			list_skb = list_skb->next;
 
 			if (unlikely(!nskb))
 				goto err;
@@ -2936,7 +2936,7 @@
 			__skb_push(nskb, doffset);
 		} else {
 			nskb = __alloc_skb(hsize + doffset + headroom,
-					   GFP_ATOMIC, skb_alloc_rx_flag(skb),
+					   GFP_ATOMIC, skb_alloc_rx_flag(head_skb),
 					   NUMA_NO_NODE);
 
 			if (unlikely(!nskb))
@@ -2952,12 +2952,12 @@
 			segs = nskb;
 		tail = nskb;
 
-		__copy_skb_header(nskb, skb);
-		nskb->mac_len = skb->mac_len;
+		__copy_skb_header(nskb, head_skb);
+		nskb->mac_len = head_skb->mac_len;
 
 		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
 
-		skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+		skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
 						 doffset + tnl_hlen);
 
@@ -2966,30 +2966,32 @@
 
 		if (!sg) {
 			nskb->ip_summed = CHECKSUM_NONE;
-			nskb->csum = skb_copy_and_csum_bits(skb, offset,
+			nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
 							    skb_put(nskb, len),
 							    len, 0);
 			continue;
 		}
 
-		frag = skb_shinfo(nskb)->frags;
+		nskb_frag = skb_shinfo(nskb)->frags;
 
-		skb_copy_from_linear_data_offset(skb, offset,
+		skb_copy_from_linear_data_offset(head_skb, offset,
 						 skb_put(nskb, hsize), hsize);
 
-		skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
+		skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags &
+			SKBTX_SHARED_FRAG;
 
 		while (pos < offset + len) {
 			if (i >= nfrags) {
-				BUG_ON(skb_headlen(fskb));
+				BUG_ON(skb_headlen(list_skb));
 
 				i = 0;
-				nfrags = skb_shinfo(fskb)->nr_frags;
-				skb_frag = skb_shinfo(fskb)->frags;
+				nfrags = skb_shinfo(list_skb)->nr_frags;
+				frag = skb_shinfo(list_skb)->frags;
+				frag_skb = list_skb;
 
 				BUG_ON(!nfrags);
 
-				fskb = fskb->next;
+				list_skb = list_skb->next;
 			}
 
 			if (unlikely(skb_shinfo(nskb)->nr_frags >=
@@ -3000,27 +3002,30 @@
 				goto err;
 			}
 
-			*frag = *skb_frag;
-			__skb_frag_ref(frag);
-			size = skb_frag_size(frag);
+			if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
+				goto err;
+
+			*nskb_frag = *frag;
+			__skb_frag_ref(nskb_frag);
+			size = skb_frag_size(nskb_frag);
 
 			if (pos < offset) {
-				frag->page_offset += offset - pos;
-				skb_frag_size_sub(frag, offset - pos);
+				nskb_frag->page_offset += offset - pos;
+				skb_frag_size_sub(nskb_frag, offset - pos);
 			}
 
 			skb_shinfo(nskb)->nr_frags++;
 
 			if (pos + size <= offset + len) {
 				i++;
-				skb_frag++;
+				frag++;
 				pos += size;
 			} else {
-				skb_frag_size_sub(frag, pos + size - (offset + len));
+				skb_frag_size_sub(nskb_frag, pos + size - (offset + len));
 				goto skip_fraglist;
 			}
 
-			frag++;
+			nskb_frag++;
 		}
 
 skip_fraglist:
@@ -3034,7 +3039,7 @@
 						  nskb->len - doffset, 0);
 			nskb->ip_summed = CHECKSUM_NONE;
 		}
-	} while ((offset += len) < skb->len);
+	} while ((offset += len) < head_skb->len);
 
 	return segs;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 5b6a943..c0fc6bd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2357,10 +2357,13 @@
 	if (sk->sk_backlog.tail)
 		__release_sock(sk);
 
+	/* Warning : release_cb() might need to release sk ownership,
+	 * ie call sock_release_ownership(sk) before us.
+	 */
 	if (sk->sk_prot->release_cb)
 		sk->sk_prot->release_cb(sk);
 
-	sk->sk_lock.owned = 0;
+	sock_release_ownership(sk);
 	if (waitqueue_active(&sk->sk_lock.wq))
 		wake_up(&sk->sk_lock.wq);
 	spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 327060c..7ae0d7f6 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -297,7 +297,7 @@
 
 void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx)
 {
-	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) {
 		WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
 		return;
 	}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ecd2c3f..19ab78a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1296,8 +1296,11 @@
 
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
-	/* Note : following gso_segment() might change skb->encapsulation */
-	udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bb075fc..3b01959 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -208,7 +208,7 @@
 	}
 
 	work = frag_mem_limit(nf) - nf->low_thresh;
-	while (work > 0) {
+	while (work > 0 || force) {
 		spin_lock(&nf->lru_lock);
 
 		if (list_empty(&nf->lru_list)) {
@@ -278,9 +278,10 @@
 
 	atomic_inc(&qp->refcnt);
 	hlist_add_head(&qp->list, &hb->chain);
+	inet_frag_lru_add(nf, qp);
 	spin_unlock(&hb->chain_lock);
 	read_unlock(&f->lock);
-	inet_frag_lru_add(nf, qp);
+
 	return qp;
 }
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8971780..73c6b63 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,9 +422,6 @@
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	to->ipvs_property = from->ipvs_property;
 #endif
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 50228be..78a89e6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -93,13 +93,14 @@
 	tunnel_dst_set(t, NULL);
 }
 
-static void tunnel_dst_reset_all(struct ip_tunnel *t)
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
 {
 	int i;
 
 	for_each_possible_cpu(i)
 		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
 }
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
 
 static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
 {
@@ -119,52 +120,6 @@
 	return (struct rtable *)dst;
 }
 
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
-						struct rtnl_link_stats64 *tot)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_sw_netstats *tstats =
-						   per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
-	}
-
-	tot->multicast = dev->stats.multicast;
-
-	tot->rx_crc_errors = dev->stats.rx_crc_errors;
-	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
-	tot->rx_length_errors = dev->stats.rx_length_errors;
-	tot->rx_frame_errors = dev->stats.rx_frame_errors;
-	tot->rx_errors = dev->stats.rx_errors;
-
-	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
-	tot->tx_dropped = dev->stats.tx_dropped;
-	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
-	tot->tx_errors = dev->stats.tx_errors;
-
-	tot->collisions  = dev->stats.collisions;
-
-	return tot;
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
 static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
 				__be16 flags, __be32 key)
 {
@@ -759,7 +714,7 @@
 		if (set_mtu)
 			dev->mtu = mtu;
 	}
-	tunnel_dst_reset_all(t);
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(dev);
 }
 
@@ -1088,7 +1043,7 @@
 	if (itn->fb_tunnel_dev != dev)
 		ip_tunnel_del(netdev_priv(dev));
 
-	tunnel_dst_reset_all(tunnel);
+	ip_tunnel_dst_reset_all(tunnel);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
 
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6156f4e..6f847dd 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -108,7 +108,6 @@
 	nf_reset(skb);
 	secpath_reset(skb);
 	skb_clear_hash_if_not_l4(skb);
-	skb_dst_drop(skb);
 	skb->vlan_tci = 0;
 	skb_set_queue_mapping(skb, 0);
 	skb->pkt_type = PACKET_HOST;
@@ -148,3 +147,49 @@
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+						struct rtnl_link_stats64 *tot)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		const struct pcpu_sw_netstats *tstats =
+						   per_cpu_ptr(dev->tstats, i);
+		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_bh(&tstats->syncp);
+			rx_packets = tstats->rx_packets;
+			tx_packets = tstats->tx_packets;
+			rx_bytes = tstats->rx_bytes;
+			tx_bytes = tstats->tx_bytes;
+		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+		tot->rx_packets += rx_packets;
+		tot->tx_packets += tx_packets;
+		tot->rx_bytes   += rx_bytes;
+		tot->tx_bytes   += tx_bytes;
+	}
+
+	tot->multicast = dev->stats.multicast;
+
+	tot->rx_crc_errors = dev->stats.rx_crc_errors;
+	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+	tot->rx_length_errors = dev->stats.rx_length_errors;
+	tot->rx_frame_errors = dev->stats.rx_frame_errors;
+	tot->rx_errors = dev->stats.rx_errors;
+
+	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+	tot->tx_dropped = dev->stats.tx_dropped;
+	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+	tot->tx_errors = dev->stats.tx_errors;
+
+	tot->collisions  = dev->stats.collisions;
+
+	return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index d551e31..7c67667 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1198,8 +1198,8 @@
 		map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
 	} else {
 		/* DNAT replies */
-		map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip);
-		map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
+		map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip);
+		map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip);
 	}
 
 	if (map.from == map.to)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9f3a2db..97c8f56 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1044,7 +1044,8 @@
 	}
 }
 
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int err, flags;
@@ -1059,11 +1060,12 @@
 	if (unlikely(tp->fastopen_req == NULL))
 		return -ENOBUFS;
 	tp->fastopen_req->data = msg;
+	tp->fastopen_req->size = size;
 
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
-	*size = tp->fastopen_req->copied;
+	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
 }
@@ -1083,7 +1085,7 @@
 
 	flags = msg->msg_flags;
 	if (flags & MSG_FASTOPEN) {
-		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
 		else if (err)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ad37bf1..2388275 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -290,8 +290,7 @@
 	left = tp->snd_cwnd - in_flight;
 	if (sk_can_gso(sk) &&
 	    left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
-	    left * tp->mss_cache < sk->sk_gso_max_size &&
-	    left < sk->sk_gso_max_segs)
+	    left < tp->xmit_size_goal_segs)
 		return true;
 	return left <= tcp_max_tso_deferred_mss(tp);
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 227cba7..eeaac39 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1945,8 +1945,9 @@
 		if (skb == tcp_send_head(sk))
 			break;
 
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
 			tp->undo_marker = 0;
+
 		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
 		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3be1672..17a11e6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -767,6 +767,17 @@
 	if (flags & (1UL << TCP_TSQ_DEFERRED))
 		tcp_tsq_handler(sk);
 
+	/* Here begins the tricky part :
+	 * We are called from release_sock() with :
+	 * 1) BH disabled
+	 * 2) sk_lock.slock spinlock held
+	 * 3) socket owned by us (sk->sk_lock.owned == 1)
+	 *
+	 * But following code is meant to be called from BH handlers,
+	 * so we should keep BH disabled, but early release socket ownership
+	 */
+	sock_release_ownership(sk);
+
 	if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
 		tcp_write_timer_handler(sk);
 		__sock_put(sk);
@@ -864,8 +875,8 @@
 
 		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
 			     fclone->fclone == SKB_FCLONE_CLONE))
-			NET_INC_STATS_BH(sock_net(sk),
-					 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+			NET_INC_STATS(sock_net(sk),
+				      LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
 
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -2337,6 +2348,7 @@
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int cur_mss;
+	int err;
 
 	/* Inconslusive MTU probe */
 	if (icsk->icsk_mtup.probe_size) {
@@ -2400,11 +2412,15 @@
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
-		return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			      -ENOBUFS;
+		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+			     -ENOBUFS;
 	} else {
-		return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
+
+	if (likely(!err))
+		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+	return err;
 }
 
 int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
@@ -2908,7 +2924,12 @@
 	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
-	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+	space = min_t(size_t, space, fo->size);
+
+	/* limit to order-0 allocations */
+	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+	syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
 				   sk->sk_allocation);
 	if (syn_data == NULL)
 		goto fallback;
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index d92e558..438a73a 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -138,6 +138,7 @@
 config IPV6_VTI
 tristate "Virtual (secure) IPv6: tunneling"
 	select IPV6_TUNNEL
+	select NET_IP_TUNNEL
 	depends on INET6_XFRM_MODE_TUNNEL
 	---help---
 	Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fdbfeca3..344e972 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1103,8 +1103,11 @@
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 140748d..8af3eb5 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@
 		found = (nexthdr == target);
 
 		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
-			if (target < 0)
+			if (target < 0 || found)
 				break;
 			return -ENOENT;
 		}
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3a..447a7fb 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@
 	int ret;
 
 	ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
-	if (!ret)
+	if (ret)
 		goto out;
 
 	ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
-	if (!ret)
+	if (ret)
 		goto out_rt;
 
 out:
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1e8683b..59f95af 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -89,7 +89,7 @@
 	unsigned int unfrag_ip6hlen;
 	u8 *prevhdr;
 	int offset = 0;
-	bool tunnel;
+	bool encap, udpfrag;
 	int nhoff;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
@@ -110,8 +110,8 @@
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
 		goto out;
 
-	tunnel = SKB_GSO_CB(skb)->encap_level > 0;
-	if (tunnel)
+	encap = SKB_GSO_CB(skb)->encap_level > 0;
+	if (encap)
 		features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
 
@@ -121,6 +121,12 @@
 
 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment)) {
 		skb_reset_transport_header(skb);
@@ -133,13 +139,9 @@
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
 		ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
-		if (tunnel) {
-			skb_reset_inner_headers(skb);
-			skb->encapsulation = 1;
-		}
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
-		if (!tunnel && proto == IPPROTO_UDP) {
+		if (udpfrag) {
 			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
 			fptr->frag_off = htons(offset);
@@ -148,6 +150,8 @@
 			offset += (ntohs(ipv6h->payload_len) -
 				   sizeof(struct frag_hdr));
 		}
+		if (encap)
+			skb_reset_inner_headers(skb);
 	}
 
 out:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 070a2fa..16f91a2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -530,9 +530,6 @@
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 	skb_copy_secmark(to, from);
 }
 
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index fb9beb7..587bbdc 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -135,6 +135,7 @@
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
 	fl6.saddr = np->saddr;
 	fl6.daddr = *daddr;
+	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 11dac21..fba54a4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1513,7 +1513,7 @@
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+	rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
 
 	if (!rt) {
 		err = -ENOMEM;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3dfbcf1..b4d74c8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,6 +475,7 @@
 		ipip6_tunnel_unlink(sitn, tunnel);
 		ipip6_tunnel_del_prl(tunnel, NULL);
 	}
+	ip_tunnel_dst_reset_all(tunnel);
 	dev_put(dev);
 }
 
@@ -1082,6 +1083,7 @@
 		t->parms.link = p->link;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 }
 
@@ -1112,6 +1114,7 @@
 	t->ip6rd.relay_prefix = relay_prefix;
 	t->ip6rd.prefixlen = ip6rd->prefixlen;
 	t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 	return 0;
 }
@@ -1271,6 +1274,7 @@
 			err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
 			break;
 		}
+		ip_tunnel_dst_reset_all(t);
 		netdev_state_change(dev);
 		break;
 
@@ -1326,6 +1330,9 @@
 
 static void ipip6_dev_free(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	free_percpu(tunnel->dst_cache);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
@@ -1375,6 +1382,12 @@
 		u64_stats_init(&ipip6_tunnel_stats->syncp);
 	}
 
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -1405,6 +1418,12 @@
 		u64_stats_init(&ipip6_fb_stats->syncp);
 	}
 
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
+	}
+
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
 	return 0;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7359f9..b261ee8 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -113,7 +113,7 @@
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 735d0f6..85d9d94 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -112,7 +112,6 @@
 	spinlock_t l2tp_session_hlist_lock;
 };
 
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
@@ -1863,7 +1862,7 @@
 /* We come here whenever a session's send_seq, cookie_len or
  * l2specific_len parameters are set.
  */
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version)
+void l2tp_session_set_header_len(struct l2tp_session *session, int version)
 {
 	if (version == L2TP_HDR_VER_2) {
 		session->hdr_len = 6;
@@ -1876,6 +1875,7 @@
 	}
 
 }
+EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
 
 struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
 {
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 1f01ba3..3f93ccd 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -263,6 +263,7 @@
 		      int length, int (*payload_hook)(struct sk_buff *skb));
 int l2tp_session_queue_purge(struct l2tp_session *session);
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
+void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 
 int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 		  int hdr_len);
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 4cfd722..bd7387a 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -578,8 +578,10 @@
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
-	if (info->attrs[L2TP_ATTR_SEND_SEQ])
+	if (info->attrs[L2TP_ATTR_SEND_SEQ]) {
 		session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]);
+		l2tp_session_set_header_len(session, session->tunnel->version);
+	}
 
 	if (info->attrs[L2TP_ATTR_LNS_MODE])
 		session->lns_mode = nla_get_u8(info->attrs[L2TP_ATTR_LNS_MODE]);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index be5fadf..5990919 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -254,12 +254,14 @@
 		po = pppox_sk(sk);
 		ppp_input(&po->chan, skb);
 	} else {
-		l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n",
-			  session->name);
+		l2tp_dbg(session, PPPOL2TP_MSG_DATA,
+			 "%s: recv %d byte data frame, passing to L2TP socket\n",
+			 session->name, data_len);
 
-		/* Not bound. Nothing we can do, so discard. */
-		atomic_long_inc(&session->stats.rx_errors);
-		kfree_skb(skb);
+		if (sock_queue_rcv_skb(sk, skb) < 0) {
+			atomic_long_inc(&session->stats.rx_errors);
+			kfree_skb(skb);
+		}
 	}
 
 	return;
@@ -1312,6 +1314,7 @@
 			po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
 				PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
 		}
+		l2tp_session_set_header_len(session, session->tunnel->version);
 		l2tp_info(session, PPPOL2TP_MSG_CONTROL,
 			  "%s: set send_seq=%d\n",
 			  session->name, session->send_seq);
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index f43613a..0c1ecfd 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -100,6 +100,12 @@
 		}
 		max_bw = max(max_bw, width);
 	}
+
+	/* use the configured bandwidth in case of monitor interface */
+	sdata = rcu_dereference(local->monitor_sdata);
+	if (sdata && rcu_access_pointer(sdata->vif.chanctx_conf) == conf)
+		max_bw = max(max_bw, conf->def.width);
+
 	rcu_read_unlock();
 
 	return max_bw;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 3701930..5e44e317 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1692,14 +1692,8 @@
 void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue);
 void ieee80211_add_pending_skb(struct ieee80211_local *local,
 			       struct sk_buff *skb);
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
-				   struct sk_buff_head *skbs,
-				   void (*fn)(void *data), void *data);
-static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local,
-					      struct sk_buff_head *skbs)
-{
-	ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL);
-}
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+				struct sk_buff_head *skbs);
 void ieee80211_flush_queues(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata);
 
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 2802f9d..ad8b377 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -36,6 +36,7 @@
 				      sdata->vif.addr);
 	nullfunc->frame_control = fc;
 	nullfunc->duration_id = 0;
+	nullfunc->seq_ctrl = 0;
 	/* no address resolution for this frame -> set addr 1 immediately */
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memset(skb_put(skb, 2), 0, 2); /* append QoS control field */
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index fc1d824..245dce9 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -222,6 +222,7 @@
 	switch (vht_oper->chan_width) {
 	case IEEE80211_VHT_CHANWIDTH_USE_HT:
 		vht_chandef.width = chandef->width;
+		vht_chandef.center_freq1 = chandef->center_freq1;
 		break;
 	case IEEE80211_VHT_CHANWIDTH_80MHZ:
 		vht_chandef.width = NL80211_CHAN_WIDTH_80;
@@ -271,6 +272,28 @@
 	ret = 0;
 
 out:
+	/*
+	 * When tracking the current AP, don't do any further checks if the
+	 * new chandef is identical to the one we're currently using for the
+	 * connection. This keeps us from playing ping-pong with regulatory,
+	 * without it the following can happen (for example):
+	 *  - connect to an AP with 80 MHz, world regdom allows 80 MHz
+	 *  - AP advertises regdom US
+	 *  - CRDA loads regdom US with 80 MHz prohibited (old database)
+	 *  - the code below detects an unsupported channel, downgrades, and
+	 *    we disconnect from the AP in the caller
+	 *  - disconnect causes CRDA to reload world regdomain and the game
+	 *    starts anew.
+	 * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881)
+	 *
+	 * It seems possible that there are still scenarios with CSA or real
+	 * bandwidth changes where a this could happen, but those cases are
+	 * less common and wouldn't completely prevent using the AP.
+	 */
+	if (tracking &&
+	    cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef))
+		return ret;
+
 	/* don't print the message below for VHT mismatch if VHT is disabled */
 	if (ret & IEEE80211_STA_DISABLE_VHT)
 		vht_chandef = *chandef;
@@ -3753,6 +3776,7 @@
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (WARN_ON(!chanctx_conf)) {
 			rcu_read_unlock();
+			sta_info_free(local, new_sta);
 			return -EINVAL;
 		}
 		rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c24ca0d..3e57f96 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1128,6 +1128,13 @@
 	       sta->sta.addr, sta->sta.aid);
 
 	if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+		/*
+		 * Clear the flag only if the other one is still set
+		 * so that the TX path won't start TX'ing new frames
+		 * directly ... In the case that the driver flag isn't
+		 * set ieee80211_sta_ps_deliver_wakeup() will clear it.
+		 */
+		clear_sta_flag(sta, WLAN_STA_PS_STA);
 		ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n",
 		       sta->sta.addr, sta->sta.aid);
 		return;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index decd30c..137a192 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -91,7 +91,7 @@
 	return -ENOENT;
 }
 
-static void cleanup_single_sta(struct sta_info *sta)
+static void __cleanup_single_sta(struct sta_info *sta)
 {
 	int ac, i;
 	struct tid_ampdu_tx *tid_tx;
@@ -99,7 +99,8 @@
 	struct ieee80211_local *local = sdata->local;
 	struct ps_data *ps;
 
-	if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
+	    test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
 		    sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 			ps = &sdata->bss->ps;
@@ -109,6 +110,7 @@
 			return;
 
 		clear_sta_flag(sta, WLAN_STA_PS_STA);
+		clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
 
 		atomic_dec(&ps->num_sta_ps);
 		sta_info_recalc_tim(sta);
@@ -139,7 +141,14 @@
 		ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending);
 		kfree(tid_tx);
 	}
+}
 
+static void cleanup_single_sta(struct sta_info *sta)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+
+	__cleanup_single_sta(sta);
 	sta_info_free(local, sta);
 }
 
@@ -330,6 +339,7 @@
 	rcu_read_unlock();
 
 	spin_lock_init(&sta->lock);
+	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
@@ -487,21 +497,26 @@
 		goto out_err;
 	}
 
-	/* notify driver */
-	err = sta_info_insert_drv_state(local, sdata, sta);
-	if (err)
-		goto out_err;
-
 	local->num_sta++;
 	local->sta_generation++;
 	smp_mb();
 
+	/* simplify things and don't accept BA sessions yet */
+	set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+
 	/* make the station visible */
 	sta_info_hash_add(local, sta);
 
 	list_add_rcu(&sta->list, &local->sta_list);
 
+	/* notify driver */
+	err = sta_info_insert_drv_state(local, sdata, sta);
+	if (err)
+		goto out_remove;
+
 	set_sta_flag(sta, WLAN_STA_INSERTED);
+	/* accept BA sessions now */
+	clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
 
 	ieee80211_recalc_min_chandef(sdata);
 	ieee80211_sta_debugfs_add(sta);
@@ -522,6 +537,12 @@
 		mesh_accept_plinks_update(sdata);
 
 	return 0;
+ out_remove:
+	sta_info_hash_del(local, sta);
+	list_del_rcu(&sta->list);
+	local->num_sta--;
+	synchronize_net();
+	__cleanup_single_sta(sta);
  out_err:
 	mutex_unlock(&local->sta_mtx);
 	rcu_read_lock();
@@ -1071,10 +1092,14 @@
 }
 EXPORT_SYMBOL(ieee80211_find_sta);
 
-static void clear_sta_ps_flags(void *_sta)
+/* powersave support code */
+void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 {
-	struct sta_info *sta = _sta;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+	struct sk_buff_head pending;
+	int filtered = 0, buffered = 0, ac;
+	unsigned long flags;
 	struct ps_data *ps;
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
@@ -1085,20 +1110,6 @@
 	else
 		return;
 
-	clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
-	if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA))
-		atomic_dec(&ps->num_sta_ps);
-}
-
-/* powersave support code */
-void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
-{
-	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct ieee80211_local *local = sdata->local;
-	struct sk_buff_head pending;
-	int filtered = 0, buffered = 0, ac;
-	unsigned long flags;
-
 	clear_sta_flag(sta, WLAN_STA_SP);
 
 	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
@@ -1109,6 +1120,8 @@
 
 	skb_queue_head_init(&pending);
 
+	/* sync with ieee80211_tx_h_unicast_ps_buf */
+	spin_lock(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1127,7 +1140,12 @@
 		buffered += tmp - count;
 	}
 
-	ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+	ieee80211_add_pending_skbs(local, &pending);
+	clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
+	clear_sta_flag(sta, WLAN_STA_PS_STA);
+	spin_unlock(&sta->ps_lock);
+
+	atomic_dec(&ps->num_sta_ps);
 
 	/* This station just woke up and isn't aware of our SMPS state */
 	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
@@ -1188,6 +1206,7 @@
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN);
 	memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN);
+	nullfunc->seq_ctrl = 0;
 
 	skb->priority = tid;
 	skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index d77ff70..d3a6d82 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -267,6 +267,7 @@
  * @drv_unblock_wk: used for driver PS unblocking
  * @listen_interval: listen interval of this station, when we're acting as AP
  * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
  * @ps_tx_buf: buffers (per AC) of frames to transmit to this station
  *	when it leaves power saving state or polls
  * @tx_filtered: buffers (per AC) of frames we already tried to
@@ -356,10 +357,8 @@
 	/* use the accessors defined below */
 	unsigned long _flags;
 
-	/*
-	 * STA powersave frame queues, no more than the internal
-	 * locking required.
-	 */
+	/* STA powersave lock and frame queues */
+	spinlock_t ps_lock;
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 97a02d3..4080c61 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -478,6 +478,20 @@
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
 			purge_old_ps_buffers(tx->local);
+
+		/* sync with ieee80211_sta_ps_deliver_wakeup */
+		spin_lock(&sta->ps_lock);
+		/*
+		 * STA woke up the meantime and all the frames on ps_tx_buf have
+		 * been queued to pending queue. No reordering can happen, go
+		 * ahead and Tx the packet.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+			spin_unlock(&sta->ps_lock);
+			return TX_CONTINUE;
+		}
+
 		if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
 			struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
 			ps_dbg(tx->sdata,
@@ -492,6 +506,7 @@
 		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+		spin_unlock(&sta->ps_lock);
 
 		if (!timer_pending(&local->sta_cleanup))
 			mod_timer(&local->sta_cleanup,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 676dc09..b8700d4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -435,9 +435,8 @@
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
 
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
-				   struct sk_buff_head *skbs,
-				   void (*fn)(void *data), void *data)
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+				struct sk_buff_head *skbs)
 {
 	struct ieee80211_hw *hw = &local->hw;
 	struct sk_buff *skb;
@@ -461,9 +460,6 @@
 		__skb_queue_tail(&local->pending[queue], skb);
 	}
 
-	if (fn)
-		fn(data);
-
 	for (i = 0; i < hw->queues; i++)
 		__ieee80211_wake_queue(hw, i,
 			IEEE80211_QUEUE_STOP_REASON_SKB_ADD);
@@ -1741,6 +1737,26 @@
 					IEEE80211_QUEUE_STOP_REASON_SUSPEND);
 
 	/*
+	 * Reconfigure sched scan if it was interrupted by FW restart or
+	 * suspend.
+	 */
+	mutex_lock(&local->mtx);
+	sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
+						lockdep_is_held(&local->mtx));
+	if (sched_scan_sdata && local->sched_scan_req)
+		/*
+		 * Sched scan stopped, but we don't want to report it. Instead,
+		 * we're trying to reschedule.
+		 */
+		if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
+							 local->sched_scan_req))
+			sched_scan_stopped = true;
+	mutex_unlock(&local->mtx);
+
+	if (sched_scan_stopped)
+		cfg80211_sched_scan_stopped(local->hw.wiphy);
+
+	/*
 	 * If this is for hw restart things are still running.
 	 * We may want to change that later, however.
 	 */
@@ -1768,26 +1784,6 @@
 	WARN_ON(1);
 #endif
 
-	/*
-	 * Reconfigure sched scan if it was interrupted by FW restart or
-	 * suspend.
-	 */
-	mutex_lock(&local->mtx);
-	sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
-						lockdep_is_held(&local->mtx));
-	if (sched_scan_sdata && local->sched_scan_req)
-		/*
-		 * Sched scan stopped, but we don't want to report it. Instead,
-		 * we're trying to reschedule.
-		 */
-		if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
-							 local->sched_scan_req))
-			sched_scan_stopped = true;
-	mutex_unlock(&local->mtx);
-
-	if (sched_scan_stopped)
-		cfg80211_sched_scan_stopped(local->hw.wiphy);
-
 	return 0;
 }
 
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 21211c6..d51422c 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -154,6 +154,11 @@
 		return IEEE80211_AC_BE;
 	}
 
+	if (skb->protocol == sdata->control_port_protocol) {
+		skb->priority = 7;
+		return ieee80211_downgrade_queue(sdata, skb);
+	}
+
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
 	rcu_read_lock();
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index bb322d0..b9f0e03 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1310,27 +1310,22 @@
 }
 
 static int
-ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
+ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 {
 #ifdef CONFIG_NF_NAT_NEEDED
 	int ret;
 
-	if (cda[CTA_NAT_DST]) {
-		ret = ctnetlink_parse_nat_setup(ct,
-						NF_NAT_MANIP_DST,
-						cda[CTA_NAT_DST]);
-		if (ret < 0)
-			return ret;
-	}
-	if (cda[CTA_NAT_SRC]) {
-		ret = ctnetlink_parse_nat_setup(ct,
-						NF_NAT_MANIP_SRC,
-						cda[CTA_NAT_SRC]);
-		if (ret < 0)
-			return ret;
-	}
-	return 0;
+	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
+					cda[CTA_NAT_DST]);
+	if (ret < 0)
+		return ret;
+
+	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
+					cda[CTA_NAT_SRC]);
+	return ret;
 #else
+	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+		return 0;
 	return -EOPNOTSUPP;
 #endif
 }
@@ -1659,11 +1654,9 @@
 			goto err2;
 	}
 
-	if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
-		err = ctnetlink_change_nat(ct, cda);
-		if (err < 0)
-			goto err2;
-	}
+	err = ctnetlink_setup_nat(ct, cda);
+	if (err < 0)
+		goto err2;
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index d3f5cd6..52ca952 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -432,15 +432,15 @@
 }
 EXPORT_SYMBOL(nf_nat_setup_info);
 
-unsigned int
-nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+static unsigned int
+__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip)
 {
 	/* Force range to this IP; let proto decide mapping for
 	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
 	 * Use reply in case it's already been mangled (eg local packet).
 	 */
 	union nf_inet_addr ip =
-		(HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+		(manip == NF_NAT_MANIP_SRC ?
 		ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
 		ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
 	struct nf_nat_range range = {
@@ -448,7 +448,13 @@
 		.min_addr	= ip,
 		.max_addr	= ip,
 	};
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+	return nf_nat_setup_info(ct, &range, manip);
+}
+
+unsigned int
+nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+	return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
 }
 EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
 
@@ -702,9 +708,9 @@
 
 static int
 nfnetlink_parse_nat(const struct nlattr *nat,
-		    const struct nf_conn *ct, struct nf_nat_range *range)
+		    const struct nf_conn *ct, struct nf_nat_range *range,
+		    const struct nf_nat_l3proto *l3proto)
 {
-	const struct nf_nat_l3proto *l3proto;
 	struct nlattr *tb[CTA_NAT_MAX+1];
 	int err;
 
@@ -714,38 +720,46 @@
 	if (err < 0)
 		return err;
 
-	rcu_read_lock();
-	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
-	if (l3proto == NULL) {
-		err = -EAGAIN;
-		goto out;
-	}
 	err = l3proto->nlattr_to_range(tb, range);
 	if (err < 0)
-		goto out;
+		return err;
 
 	if (!tb[CTA_NAT_PROTO])
-		goto out;
+		return 0;
 
-	err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
-out:
-	rcu_read_unlock();
-	return err;
+	return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
 }
 
+/* This function is called under rcu_read_lock() */
 static int
 nfnetlink_parse_nat_setup(struct nf_conn *ct,
 			  enum nf_nat_manip_type manip,
 			  const struct nlattr *attr)
 {
 	struct nf_nat_range range;
+	const struct nf_nat_l3proto *l3proto;
 	int err;
 
-	err = nfnetlink_parse_nat(attr, ct, &range);
+	/* Should not happen, restricted to creating new conntracks
+	 * via ctnetlink.
+	 */
+	if (WARN_ON_ONCE(nf_nat_initialized(ct, manip)))
+		return -EEXIST;
+
+	/* Make sure that L3 NAT is there by when we call nf_nat_setup_info to
+	 * attach the null binding, otherwise this may oops.
+	 */
+	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
+	if (l3proto == NULL)
+		return -EAGAIN;
+
+	/* No NAT information has been passed, allocate the null-binding */
+	if (attr == NULL)
+		return __nf_nat_alloc_null_binding(ct, manip);
+
+	err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
 	if (err < 0)
 		return err;
-	if (nf_nat_initialized(ct, manip))
-		return -EEXIST;
 
 	return nf_nat_setup_info(ct, &range, manip);
 }
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e8254ad..425cf39 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -116,7 +116,7 @@
 				 skb->sk->sk_socket->file->f_cred->fsgid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 		break;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	case NFT_META_RTCLASSID: {
 		const struct dst_entry *dst = skb_dst(skb);
 
@@ -199,7 +199,7 @@
 	case NFT_META_OIFTYPE:
 	case NFT_META_SKUID:
 	case NFT_META_SKGID:
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	case NFT_META_RTCLASSID:
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a2aeb31..85daa84 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -135,7 +135,8 @@
 	if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
 		return ERR_PTR(-EINVAL);
 
-	if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)
+	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
+	    base != NFT_PAYLOAD_LL_HEADER)
 		return &nft_payload_fast_ops;
 	else
 		return &nft_payload_ops;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 8a310f2..b718a52 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -21,9 +21,9 @@
 {
 	switch (pkt->ops->pf) {
 	case NFPROTO_IPV4:
-		nft_reject_ipv4_eval(expr, data, pkt);
+		return nft_reject_ipv4_eval(expr, data, pkt);
 	case NFPROTO_IPV6:
-		nft_reject_ipv6_eval(expr, data, pkt);
+		return nft_reject_ipv6_eval(expr, data, pkt);
 	}
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fdf5135..04748ab6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1489,8 +1489,8 @@
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
-	/* Only superuser is allowed to send multicasts */
-	if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	if ((nladdr->nl_groups || nladdr->nl_pid) &&
+	    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 46bda01..56db888 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -301,7 +301,7 @@
 	rc = __nci_request(ndev, nci_reset_req, 0,
 			   msecs_to_jiffies(NCI_RESET_TIMEOUT));
 
-	if (ndev->ops->setup(ndev))
+	if (ndev->ops->setup)
 		ndev->ops->setup(ndev);
 
 	if (!rc) {
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1313145..a07d55e 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -273,11 +273,12 @@
 
 void qdisc_list_add(struct Qdisc *q)
 {
-	struct Qdisc *root = qdisc_dev(q)->qdisc;
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		struct Qdisc *root = qdisc_dev(q)->qdisc;
 
-	WARN_ON_ONCE(root == &noop_qdisc);
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
+		WARN_ON_ONCE(root == &noop_qdisc);
 		list_add_tail(&q->list, &root->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 08ef7a4..21e2517 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -601,6 +601,7 @@
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct rb_root *array;
+	void *old_fq_root;
 	u32 idx;
 
 	if (q->fq_root && log == q->fq_trees_log)
@@ -615,13 +616,19 @@
 	for (idx = 0; idx < (1U << log); idx++)
 		array[idx] = RB_ROOT;
 
-	if (q->fq_root) {
-		fq_rehash(q, q->fq_root, q->fq_trees_log, array, log);
-		fq_free(q->fq_root);
-	}
+	sch_tree_lock(sch);
+
+	old_fq_root = q->fq_root;
+	if (old_fq_root)
+		fq_rehash(q, old_fq_root, q->fq_trees_log, array, log);
+
 	q->fq_root = array;
 	q->fq_trees_log = log;
 
+	sch_tree_unlock(sch);
+
+	fq_free(old_fq_root);
+
 	return 0;
 }
 
@@ -697,9 +704,11 @@
 		q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
 	}
 
-	if (!err)
+	if (!err) {
+		sch_tree_unlock(sch);
 		err = fq_resize(sch, fq_log);
-
+		sch_tree_lock(sch);
+	}
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_dequeue(sch);
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1cb413f..4f505a0 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -334,18 +334,6 @@
 			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
 						      tb[TCA_TBF_PTAB]));
 
-	if (q->qdisc != &noop_qdisc) {
-		err = fifo_set_limit(q->qdisc, qopt->limit);
-		if (err)
-			goto done;
-	} else if (qopt->limit > 0) {
-		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
-		if (IS_ERR(child)) {
-			err = PTR_ERR(child);
-			goto done;
-		}
-	}
-
 	buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
 	mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
 
@@ -390,6 +378,18 @@
 		goto done;
 	}
 
+	if (q->qdisc != &noop_qdisc) {
+		err = fifo_set_limit(q->qdisc, qopt->limit);
+		if (err)
+			goto done;
+	} else if (qopt->limit > 0) {
+		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
+		if (IS_ERR(child)) {
+			err = PTR_ERR(child);
+			goto done;
+		}
+	}
+
 	sch_tree_lock(sch);
 	if (child) {
 		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index f558433..ee13d28 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1239,78 +1239,107 @@
 }
 
 /* Update the retran path for sending a retransmitted packet.
- * Round-robin through the active transports, else round-robin
- * through the inactive transports as this is the next best thing
- * we can try.
+ * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints:
+ *
+ *   When there is outbound data to send and the primary path
+ *   becomes inactive (e.g., due to failures), or where the
+ *   SCTP user explicitly requests to send data to an
+ *   inactive destination transport address, before reporting
+ *   an error to its ULP, the SCTP endpoint should try to send
+ *   the data to an alternate active destination transport
+ *   address if one exists.
+ *
+ *   When retransmitting data that timed out, if the endpoint
+ *   is multihomed, it should consider each source-destination
+ *   address pair in its retransmission selection policy.
+ *   When retransmitting timed-out data, the endpoint should
+ *   attempt to pick the most divergent source-destination
+ *   pair from the original source-destination pair to which
+ *   the packet was transmitted.
+ *
+ *   Note: Rules for picking the most divergent source-destination
+ *   pair are an implementation decision and are not specified
+ *   within this document.
+ *
+ * Our basic strategy is to round-robin transports in priorities
+ * according to sctp_state_prio_map[] e.g., if no such
+ * transport with state SCTP_ACTIVE exists, round-robin through
+ * SCTP_UNKNOWN, etc. You get the picture.
  */
-void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+static const u8 sctp_trans_state_to_prio_map[] = {
+	[SCTP_ACTIVE]	= 3,	/* best case */
+	[SCTP_UNKNOWN]	= 2,
+	[SCTP_PF]	= 1,
+	[SCTP_INACTIVE] = 0,	/* worst case */
+};
+
+static u8 sctp_trans_score(const struct sctp_transport *trans)
 {
-	struct sctp_transport *t, *next;
-	struct list_head *head = &asoc->peer.transport_addr_list;
-	struct list_head *pos;
-
-	if (asoc->peer.transport_count == 1)
-		return;
-
-	/* Find the next transport in a round-robin fashion. */
-	t = asoc->peer.retran_path;
-	pos = &t->transports;
-	next = NULL;
-
-	while (1) {
-		/* Skip the head. */
-		if (pos->next == head)
-			pos = head->next;
-		else
-			pos = pos->next;
-
-		t = list_entry(pos, struct sctp_transport, transports);
-
-		/* We have exhausted the list, but didn't find any
-		 * other active transports.  If so, use the next
-		 * transport.
-		 */
-		if (t == asoc->peer.retran_path) {
-			t = next;
-			break;
-		}
-
-		/* Try to find an active transport. */
-
-		if ((t->state == SCTP_ACTIVE) ||
-		    (t->state == SCTP_UNKNOWN)) {
-			break;
-		} else {
-			/* Keep track of the next transport in case
-			 * we don't find any active transport.
-			 */
-			if (t->state != SCTP_UNCONFIRMED && !next)
-				next = t;
-		}
-	}
-
-	if (t)
-		asoc->peer.retran_path = t;
-	else
-		t = asoc->peer.retran_path;
-
-	pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc,
-		 &t->ipaddr.sa);
+	return sctp_trans_state_to_prio_map[trans->state];
 }
 
-/* Choose the transport for sending retransmit packet.  */
-struct sctp_transport *sctp_assoc_choose_alter_transport(
-	struct sctp_association *asoc, struct sctp_transport *last_sent_to)
+static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
+						    struct sctp_transport *best)
+{
+	if (best == NULL)
+		return curr;
+
+	return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+}
+
+void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+{
+	struct sctp_transport *trans = asoc->peer.retran_path;
+	struct sctp_transport *trans_next = NULL;
+
+	/* We're done as we only have the one and only path. */
+	if (asoc->peer.transport_count == 1)
+		return;
+	/* If active_path and retran_path are the same and active,
+	 * then this is the only active path. Use it.
+	 */
+	if (asoc->peer.active_path == asoc->peer.retran_path &&
+	    asoc->peer.active_path->state == SCTP_ACTIVE)
+		return;
+
+	/* Iterate from retran_path's successor back to retran_path. */
+	for (trans = list_next_entry(trans, transports); 1;
+	     trans = list_next_entry(trans, transports)) {
+		/* Manually skip the head element. */
+		if (&trans->transports == &asoc->peer.transport_addr_list)
+			continue;
+		if (trans->state == SCTP_UNCONFIRMED)
+			continue;
+		trans_next = sctp_trans_elect_best(trans, trans_next);
+		/* Active is good enough for immediate return. */
+		if (trans_next->state == SCTP_ACTIVE)
+			break;
+		/* We've reached the end, time to update path. */
+		if (trans == asoc->peer.retran_path)
+			break;
+	}
+
+	if (trans_next != NULL)
+		asoc->peer.retran_path = trans_next;
+
+	pr_debug("%s: association:%p updated new path to addr:%pISpc\n",
+		 __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
+}
+
+struct sctp_transport *
+sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
+				  struct sctp_transport *last_sent_to)
 {
 	/* If this is the first time packet is sent, use the active path,
 	 * else use the retran path. If the last packet was sent over the
 	 * retran path, update the retran path and use it.
 	 */
-	if (!last_sent_to)
+	if (last_sent_to == NULL) {
 		return asoc->peer.active_path;
-	else {
+	} else {
 		if (last_sent_to == asoc->peer.retran_path)
 			sctp_assoc_update_retran_path(asoc);
+
 		return asoc->peer.retran_path;
 	}
 }
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 632090b..3a1767e 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1421,8 +1421,8 @@
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index bd85915..5d6883f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -495,11 +495,12 @@
 	}
 
 	/* If the transport error count is greater than the pf_retrans
-	 * threshold, and less than pathmaxrtx, then mark this transport
-	 * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
-	 * point 1
+	 * threshold, and less than pathmaxrtx, and if the current state
+	 * is not SCTP_UNCONFIRMED, then mark this transport as Partially
+	 * Failed, see SCTP Quick Failover Draft, section 5.1
 	 */
 	if ((transport->state != SCTP_PF) &&
+	   (transport->state != SCTP_UNCONFIRMED) &&
 	   (asoc->pf_retrans < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 591b44d..01e0024 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -758,6 +758,12 @@
 		struct sctp_chunk auth;
 		sctp_ierror_t ret;
 
+		/* Make sure that we and the peer are AUTH capable */
+		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+			sctp_association_free(new_asoc);
+			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+		}
+
 		/* set-up our fake chunk so that we can process it */
 		auth.skb = chunk->auth_chunk;
 		auth.asoc = chunk->asoc;
@@ -768,10 +774,6 @@
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
diff --git a/net/socket.c b/net/socket.c
index 879933a..a19ae19 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -450,16 +450,17 @@
 
 static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	struct socket *sock;
 
 	*err = -EBADF;
-	file = fget_light(fd, fput_needed);
-	if (file) {
-		sock = sock_from_file(file, err);
-		if (sock)
+	if (f.file) {
+		sock = sock_from_file(f.file, err);
+		if (likely(sock)) {
+			*fput_needed = f.flags;
 			return sock;
-		fput_light(file, *fput_needed);
+		}
+		fdput(f);
 	}
 	return NULL;
 }
@@ -1985,6 +1986,10 @@
 {
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index a38c899..574b861 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -610,8 +610,13 @@
 
 int tipc_bearer_setup(void)
 {
+	int err;
+
+	err = register_netdevice_notifier(&notifier);
+	if (err)
+		return err;
 	dev_add_pack(&tipc_packet_type);
-	return register_netdevice_notifier(&notifier);
+	return 0;
 }
 
 void tipc_bearer_cleanup(void)
diff --git a/net/tipc/config.c b/net/tipc/config.c
index c301a9a..e6d7216 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -181,7 +181,7 @@
 	if (tipc_own_addr)
 		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 						   " (cannot change node address once assigned)");
-	tipc_core_start_net(addr);
+	tipc_net_start(addr);
 	return tipc_cfg_reply_none();
 }
 
@@ -376,7 +376,6 @@
 	struct tipc_cfg_msg_hdr *req_hdr;
 	struct tipc_cfg_msg_hdr *rep_hdr;
 	struct sk_buff *rep_buf;
-	int ret;
 
 	/* Validate configuration message header (ignore invalid message) */
 	req_hdr = (struct tipc_cfg_msg_hdr *)buf;
@@ -398,12 +397,8 @@
 		memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr));
 		rep_hdr->tcm_len = htonl(rep_buf->len);
 		rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST);
-
-		ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data,
-					rep_buf->len);
-		if (ret < 0)
-			pr_err("Sending cfg reply message failed, no memory\n");
-
+		tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data,
+				  rep_buf->len);
 		kfree_skb(rep_buf);
 	}
 }
diff --git a/net/tipc/core.c b/net/tipc/core.c
index f9e88d8..80c2064 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -77,37 +77,13 @@
 }
 
 /**
- * tipc_core_stop_net - shut down TIPC networking sub-systems
- */
-static void tipc_core_stop_net(void)
-{
-	tipc_net_stop();
-	tipc_bearer_cleanup();
-}
-
-/**
- * start_net - start TIPC networking sub-systems
- */
-int tipc_core_start_net(unsigned long addr)
-{
-	int res;
-
-	tipc_net_start(addr);
-	res = tipc_bearer_setup();
-	if (res < 0)
-		goto err;
-	return res;
-
-err:
-	tipc_core_stop_net();
-	return res;
-}
-
-/**
  * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
  */
 static void tipc_core_stop(void)
 {
+	tipc_handler_stop();
+	tipc_net_stop();
+	tipc_bearer_cleanup();
 	tipc_netlink_stop();
 	tipc_cfg_stop();
 	tipc_subscr_stop();
@@ -122,30 +98,65 @@
  */
 static int tipc_core_start(void)
 {
-	int res;
+	int err;
 
 	get_random_bytes(&tipc_random, sizeof(tipc_random));
 
-	res = tipc_handler_start();
-	if (!res)
-		res = tipc_ref_table_init(tipc_max_ports, tipc_random);
-	if (!res)
-		res = tipc_nametbl_init();
-	if (!res)
-		res = tipc_netlink_start();
-	if (!res)
-		res = tipc_socket_init();
-	if (!res)
-		res = tipc_register_sysctl();
-	if (!res)
-		res = tipc_subscr_start();
-	if (!res)
-		res = tipc_cfg_init();
-	if (res) {
-		tipc_handler_stop();
-		tipc_core_stop();
-	}
-	return res;
+	err = tipc_handler_start();
+	if (err)
+		goto out_handler;
+
+	err = tipc_ref_table_init(tipc_max_ports, tipc_random);
+	if (err)
+		goto out_reftbl;
+
+	err = tipc_nametbl_init();
+	if (err)
+		goto out_nametbl;
+
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
+	err = tipc_register_sysctl();
+	if (err)
+		goto out_sysctl;
+
+	err = tipc_subscr_start();
+	if (err)
+		goto out_subscr;
+
+	err = tipc_cfg_init();
+	if (err)
+		goto out_cfg;
+
+	err = tipc_bearer_setup();
+	if (err)
+		goto out_bearer;
+
+	return 0;
+out_bearer:
+	tipc_cfg_stop();
+out_cfg:
+	tipc_subscr_stop();
+out_subscr:
+	tipc_unregister_sysctl();
+out_sysctl:
+	tipc_socket_stop();
+out_socket:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_nametbl_stop();
+out_nametbl:
+	tipc_ref_table_stop();
+out_reftbl:
+	tipc_handler_stop();
+out_handler:
+	return err;
 }
 
 static int __init tipc_init(void)
@@ -174,8 +185,6 @@
 
 static void __exit tipc_exit(void)
 {
-	tipc_handler_stop();
-	tipc_core_stop_net();
 	tipc_core_stop();
 	pr_info("Deactivated\n");
 }
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 5569d96..4dfe137 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -90,7 +90,6 @@
 /*
  * Routines available to privileged subsystems
  */
-int tipc_core_start_net(unsigned long);
 int tipc_handler_start(void);
 void tipc_handler_stop(void);
 int tipc_netlink_start(void);
diff --git a/net/tipc/handler.c b/net/tipc/handler.c
index e4bc8a2..1fabf16 100644
--- a/net/tipc/handler.c
+++ b/net/tipc/handler.c
@@ -58,7 +58,6 @@
 
 	spin_lock_bh(&qitem_lock);
 	if (!handler_enabled) {
-		pr_err("Signal request ignored by handler\n");
 		spin_unlock_bh(&qitem_lock);
 		return -ENOPROTOOPT;
 	}
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 92a1533..042e8e3 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -941,20 +941,48 @@
 	return 0;
 }
 
+/**
+ * tipc_purge_publications - remove all publications for a given type
+ *
+ * tipc_nametbl_lock must be held when calling this function
+ */
+static void tipc_purge_publications(struct name_seq *seq)
+{
+	struct publication *publ, *safe;
+	struct sub_seq *sseq;
+	struct name_info *info;
+
+	if (!seq->sseqs) {
+		nameseq_delete_empty(seq);
+		return;
+	}
+	sseq = seq->sseqs;
+	info = sseq->info;
+	list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
+		tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node,
+					 publ->ref, publ->key);
+	}
+}
+
 void tipc_nametbl_stop(void)
 {
 	u32 i;
+	struct name_seq *seq;
+	struct hlist_head *seq_head;
+	struct hlist_node *safe;
 
-	if (!table.types)
-		return;
-
-	/* Verify name table is empty, then release it */
+	/* Verify name table is empty and purge any lingering
+	 * publications, then release the name table
+	 */
 	write_lock_bh(&tipc_nametbl_lock);
 	for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
 		if (hlist_empty(&table.types[i]))
 			continue;
-		pr_err("nametbl_stop(): orphaned hash chain detected\n");
-		break;
+		seq_head = &table.types[i];
+		hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
+			tipc_purge_publications(seq);
+		}
+		continue;
 	}
 	kfree(table.types);
 	table.types = NULL;
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9f72a63..3aaf73d 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -83,8 +83,6 @@
 	},
 };
 
-static int tipc_genl_family_registered;
-
 int tipc_netlink_start(void)
 {
 	int res;
@@ -94,16 +92,10 @@
 		pr_err("Failed to register netlink interface\n");
 		return res;
 	}
-
-	tipc_genl_family_registered = 1;
 	return 0;
 }
 
 void tipc_netlink_stop(void)
 {
-	if (!tipc_genl_family_registered)
-		return;
-
 	genl_unregister_family(&tipc_genl_family);
-	tipc_genl_family_registered = 0;
 }
diff --git a/net/tipc/ref.c b/net/tipc/ref.c
index 2a2a938..de3d593 100644
--- a/net/tipc/ref.c
+++ b/net/tipc/ref.c
@@ -126,9 +126,6 @@
  */
 void tipc_ref_table_stop(void)
 {
-	if (!tipc_ref_table.entries)
-		return;
-
 	vfree(tipc_ref_table.entries);
 	tipc_ref_table.entries = NULL;
 }
diff --git a/net/tipc/server.c b/net/tipc/server.c
index b635ca3..646a930 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -87,7 +87,6 @@
 static void tipc_conn_kref_release(struct kref *kref)
 {
 	struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
-	struct tipc_server *s = con->server;
 
 	if (con->sock) {
 		tipc_sock_release_local(con->sock);
@@ -95,10 +94,6 @@
 	}
 
 	tipc_clean_outqueues(con);
-
-	if (con->conid)
-		s->tipc_conn_shutdown(con->conid, con->usr_data);
-
 	kfree(con);
 }
 
@@ -181,6 +176,9 @@
 	struct tipc_server *s = con->server;
 
 	if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
+		if (con->conid)
+			s->tipc_conn_shutdown(con->conid, con->usr_data);
+
 		spin_lock_bh(&s->idr_lock);
 		idr_remove(&s->conn_idr, con->conid);
 		s->idr_in_use--;
@@ -429,10 +427,12 @@
 	list_add_tail(&e->list, &con->outqueue);
 	spin_unlock_bh(&con->outqueue_lock);
 
-	if (test_bit(CF_CONNECTED, &con->flags))
+	if (test_bit(CF_CONNECTED, &con->flags)) {
 		if (!queue_work(s->send_wq, &con->swork))
 			conn_put(con);
-
+	} else {
+		conn_put(con);
+	}
 	return 0;
 }
 
@@ -573,7 +573,6 @@
 		kmem_cache_destroy(s->rcvbuf_cache);
 		return ret;
 	}
-	s->enabled = 1;
 	return ret;
 }
 
@@ -583,10 +582,6 @@
 	int total = 0;
 	int id;
 
-	if (!s->enabled)
-		return;
-
-	s->enabled = 0;
 	spin_lock_bh(&s->idr_lock);
 	for (id = 0; total < s->idr_in_use; id++) {
 		con = idr_find(&s->conn_idr, id);
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 98b23f2..be817b0 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -56,7 +56,6 @@
  * @name: server name
  * @imp: message importance
  * @type: socket type
- * @enabled: identify whether server is launched or not
  */
 struct tipc_server {
 	struct idr conn_idr;
@@ -74,7 +73,6 @@
 	const char name[TIPC_SERVER_NAME_LEN];
 	int imp;
 	int type;
-	int enabled;
 };
 
 int tipc_conn_sendmsg(struct tipc_server *s, int conid,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index aab4948..0ed0eaa 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -70,8 +70,6 @@
 static struct proto tipc_proto;
 static struct proto tipc_proto_kern;
 
-static int sockets_enabled;
-
 /*
  * Revised TIPC socket locking policy:
  *
@@ -999,7 +997,7 @@
 
 	for (;;) {
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		if (skb_queue_empty(&sk->sk_receive_queue)) {
+		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
 			if (sock->state == SS_DISCONNECTING) {
 				err = -ENOTCONN;
 				break;
@@ -1625,7 +1623,7 @@
 	for (;;) {
 		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
 					  TASK_INTERRUPTIBLE);
-		if (skb_queue_empty(&sk->sk_receive_queue)) {
+		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
 			release_sock(sk);
 			timeo = schedule_timeout(timeo);
 			lock_sock(sk);
@@ -2027,8 +2025,6 @@
 		proto_unregister(&tipc_proto);
 		goto out;
 	}
-
-	sockets_enabled = 1;
  out:
 	return res;
 }
@@ -2038,10 +2034,6 @@
  */
 void tipc_socket_stop(void)
 {
-	if (!sockets_enabled)
-		return;
-
-	sockets_enabled = 0;
 	sock_unregister(tipc_family_ops.family);
 	proto_unregister(&tipc_proto);
 }
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 7cb0bd5..11c9ae0 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -96,20 +96,16 @@
 {
 	struct tipc_subscriber *subscriber = sub->subscriber;
 	struct kvec msg_sect;
-	int ret;
 
 	msg_sect.iov_base = (void *)&sub->evt;
 	msg_sect.iov_len = sizeof(struct tipc_event);
-
 	sub->evt.event = htohl(event, sub->swap);
 	sub->evt.found_lower = htohl(found_lower, sub->swap);
 	sub->evt.found_upper = htohl(found_upper, sub->swap);
 	sub->evt.port.ref = htohl(port_ref, sub->swap);
 	sub->evt.port.node = htohl(node, sub->swap);
-	ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL,
-				msg_sect.iov_base, msg_sect.iov_len);
-	if (ret < 0)
-		pr_err("Sending subscription event failed, no memory\n");
+	tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base,
+			  msg_sect.iov_len);
 }
 
 /**
@@ -153,14 +149,6 @@
 	/* The spin lock per subscriber is used to protect its members */
 	spin_lock_bh(&subscriber->lock);
 
-	/* Validate if the connection related to the subscriber is
-	 * closed (in case subscriber is terminating)
-	 */
-	if (subscriber->conid == 0) {
-		spin_unlock_bh(&subscriber->lock);
-		return;
-	}
-
 	/* Validate timeout (in case subscription is being cancelled) */
 	if (sub->timeout == TIPC_WAIT_FOREVER) {
 		spin_unlock_bh(&subscriber->lock);
@@ -215,9 +203,6 @@
 
 	spin_lock_bh(&subscriber->lock);
 
-	/* Invalidate subscriber reference */
-	subscriber->conid = 0;
-
 	/* Destroy any existing subscriptions for subscriber */
 	list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list,
 				 subscription_list) {
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 29fc8bee..ce6ec6c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -163,9 +163,8 @@
 
 static inline unsigned int unix_hash_fold(__wsum n)
 {
-	unsigned int hash = (__force unsigned int)n;
+	unsigned int hash = (__force unsigned int)csum_fold(n);
 
-	hash ^= hash>>16;
 	hash ^= hash>>8;
 	return hash&(UNIX_HASH_SIZE-1);
 }
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 010892b..a3bf18d 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -788,8 +788,6 @@
 	default:
 		break;
 	}
-
-	wdev->beacon_interval = 0;
 }
 
 static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 9b897fc..f054137 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1700,7 +1700,7 @@
 		return;
 	case NL80211_REGDOM_SET_BY_USER:
 		treatment = reg_process_hint_user(reg_request);
-		if (treatment == REG_REQ_OK ||
+		if (treatment == REG_REQ_IGNORE ||
 		    treatment == REG_REQ_ALREADY_SET)
 			return;
 		schedule_delayed_work(&reg_timeout, msecs_to_jiffies(3142));
@@ -2373,6 +2373,7 @@
 int set_regdom(const struct ieee80211_regdomain *rd)
 {
 	struct regulatory_request *lr;
+	bool user_reset = false;
 	int r;
 
 	if (!reg_is_valid_request(rd->alpha2)) {
@@ -2389,6 +2390,7 @@
 		break;
 	case NL80211_REGDOM_SET_BY_USER:
 		r = reg_set_rd_user(rd, lr);
+		user_reset = true;
 		break;
 	case NL80211_REGDOM_SET_BY_DRIVER:
 		r = reg_set_rd_driver(rd, lr);
@@ -2402,8 +2404,14 @@
 	}
 
 	if (r) {
-		if (r == -EALREADY)
+		switch (r) {
+		case -EALREADY:
 			reg_set_request_processed();
+			break;
+		default:
+			/* Back to world regulatory in case of errors */
+			restore_regulatory_settings(user_reset);
+		}
 
 		kfree(rd);
 		return r;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4b98b25..1d5c7bf 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1158,7 +1158,7 @@
 	if (hlist_unhashed(&pol->bydst))
 		return NULL;
 
-	hlist_del(&pol->bydst);
+	hlist_del_init(&pol->bydst);
 	hlist_del(&pol->byidx);
 	list_del(&pol->walk.all);
 	net->xfrm.policy_count[dir]--;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a26b7aa..40f1b3e 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1159,6 +1159,11 @@
 	}
 	x->props.aalgo = orig->props.aalgo;
 
+	if (orig->aead) {
+		x->aead = xfrm_algo_aead_clone(orig->aead);
+		if (!x->aead)
+			goto error;
+	}
 	if (orig->ealg) {
 		x->ealg = xfrm_algo_clone(orig->ealg);
 		if (!x->ealg)
@@ -1201,6 +1206,9 @@
 	x->props.flags = orig->props.flags;
 	x->props.extra_flags = orig->props.extra_flags;
 
+	x->tfcpad = orig->tfcpad;
+	x->replay_maxdiff = orig->replay_maxdiff;
+	x->replay_maxage = orig->replay_maxage;
 	x->curlft.add_time = orig->curlft.add_time;
 	x->km.state = orig->km.state;
 	x->km.seq = orig->km.seq;
@@ -1215,11 +1223,12 @@
 	return NULL;
 }
 
-/* net->xfrm.xfrm_state_lock is held */
 struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
 {
 	unsigned int h;
-	struct xfrm_state *x;
+	struct xfrm_state *x = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (m->reqid) {
 		h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1236,7 +1245,7 @@
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	} else {
 		h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1251,11 +1260,13 @@
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	}
 
-	return NULL;
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	return x;
 }
 EXPORT_SYMBOL(xfrm_migrate_state_find);
 
@@ -1451,7 +1462,7 @@
 {
 	int err = 0;
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	struct net *net = xs_net(*dst);
+	struct net *net = xs_net(*src);
 
 	if (!afinfo)
 		return -EAFNOSUPPORT;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 1ae3ec7..c274179 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -32,11 +32,6 @@
 #include <linux/in6.h>
 #endif
 
-static inline int aead_len(struct xfrm_algo_aead *alg)
-{
-	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
-}
-
 static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
 {
 	struct nlattr *rt = attrs[type];
diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh
index ef47409..17fa901 100644
--- a/scripts/gen_initramfs_list.sh
+++ b/scripts/gen_initramfs_list.sh
@@ -257,7 +257,7 @@
                 && compr="lzop -9 -f"
 		echo "$output_file" | grep -q "\.lz4$" \
                 && [ -x "`which lz4 2> /dev/null`" ] \
-                && compr="lz4 -9 -f"
+                && compr="lz4 -l -9 -f"
 		echo "$output_file" | grep -q "\.cpio$" && compr="cat"
 		shift
 		;;
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 4061098..99a45fd 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1502,6 +1502,16 @@
 #define R_ARM_JUMP24	29
 #endif
 
+#ifndef	R_ARM_THM_CALL
+#define	R_ARM_THM_CALL		10
+#endif
+#ifndef	R_ARM_THM_JUMP24
+#define	R_ARM_THM_JUMP24	30
+#endif
+#ifndef	R_ARM_THM_JUMP19
+#define	R_ARM_THM_JUMP19	51
+#endif
+
 static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
 {
 	unsigned int r_typ = ELF_R_TYPE(r->r_info);
@@ -1515,6 +1525,9 @@
 	case R_ARM_PC24:
 	case R_ARM_CALL:
 	case R_ARM_JUMP24:
+	case R_ARM_THM_CALL:
+	case R_ARM_THM_JUMP24:
+	case R_ARM_THM_JUMP19:
 		/* From ARM ABI: ((S + A) | T) - P */
 		r->r_addend = (int)(long)(elf->hdr +
 		              sechdr->sh_offset +
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index d46cbc5..2fb2576 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1000,7 +1000,11 @@
 
 	kenter("{%d}", key->serial);
 
-	BUG_ON(key != ctx->match_data);
+	/* We might get a keyring with matching index-key that is nonetheless a
+	 * different keyring. */
+	if (key != ctx->match_data)
+		return 0;
+
 	ctx->result = ERR_PTR(-EDEADLK);
 	return 1;
 }
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index c0f4988..9c5cdc2ca 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -3338,10 +3338,10 @@
 	if (rc)
 		return rc;
 
-	buf[0] = ft->stype;
-	buf[1] = ft->ttype;
-	buf[2] = ft->tclass;
-	buf[3] = otype->otype;
+	buf[0] = cpu_to_le32(ft->stype);
+	buf[1] = cpu_to_le32(ft->ttype);
+	buf[2] = cpu_to_le32(ft->tclass);
+	buf[3] = cpu_to_le32(otype->otype);
 
 	rc = put_entry(buf, sizeof(u32), 4, fp);
 	if (rc)
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index df3652a..8ed0bcc 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -1026,6 +1026,9 @@
 		spec->gen.keep_eapd_on = 1;
 		spec->gen.vmaster_mute.hook = ad_vmaster_eapd_hook;
 		spec->eapd_nid = 0x12;
+		/* Analog PC Beeper - allow firmware/ACPI beeps */
+		spec->beep_amp = HDA_COMPOSE_AMP_VAL(0x20, 3, 3, HDA_INPUT);
+		spec->gen.beep_nid = 0; /* no digital beep */
 	}
 }
 
@@ -1092,6 +1095,7 @@
 	spec = codec->spec;
 
 	spec->gen.mixer_nid = 0x20;
+	spec->gen.mixer_merge_nid = 0x21;
 	spec->gen.beep_nid = 0x10;
 	set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 6eb903c..8d0a844 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3616,6 +3616,19 @@
 	}
 }
 
+static void alc_no_shutup(struct hda_codec *codec)
+{
+}
+
+static void alc_fixup_no_shutup(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		struct alc_spec *spec = codec->spec;
+		spec->shutup = alc_no_shutup;
+	}
+}
+
 static void alc_fixup_headset_mode_alc668(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -3844,6 +3857,7 @@
 	ALC269_FIXUP_HP_GPIO_LED,
 	ALC269_FIXUP_INV_DMIC,
 	ALC269_FIXUP_LENOVO_DOCK,
+	ALC269_FIXUP_NO_SHUTUP,
 	ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
 	ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -4020,6 +4034,10 @@
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic_0x12,
 	},
+	[ALC269_FIXUP_NO_SHUTUP] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_no_shutup,
+	},
 	[ALC269_FIXUP_LENOVO_DOCK] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4253,6 +4271,7 @@
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1025, 0x0283, "Acer TravelMate 8371", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700),
@@ -4319,6 +4338,54 @@
 	SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
+	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22a0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22b2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c1, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22cd, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22ce, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22d0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	/* ALC290 */
+	SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2261, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2262, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2265, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2280, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2281, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2282, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2289, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c5, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c6, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4356,6 +4423,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5115,7 +5183,7 @@
 	SND_PCI_QUIRK(0x1028, 0x0625, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0628, "Dell", ALC668_FIXUP_AUTO_MUTE),
-	SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_AUTO_MUTE),
 	SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
 	SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP),
 	SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index a2f11bf..3bc29c9 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -98,6 +98,7 @@
 	STAC_92HD83XXX_HP_LED,
 	STAC_92HD83XXX_HP_INV_LED,
 	STAC_92HD83XXX_HP_MIC_LED,
+	STAC_HP_LED_GPIO10,
 	STAC_92HD83XXX_HEADSET_JACK,
 	STAC_92HD83XXX_HP,
 	STAC_HP_ENVY_BASS,
@@ -2130,6 +2131,17 @@
 	}
 }
 
+static void stac92hd83xxx_fixup_hp_led_gpio10(struct hda_codec *codec,
+				   const struct hda_fixup *fix, int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->gpio_led = 0x10; /* GPIO4 */
+		spec->default_polarity = 0;
+	}
+}
+
 static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -2624,6 +2636,12 @@
 		.chained = true,
 		.chain_id = STAC_92HD83XXX_HP,
 	},
+	[STAC_HP_LED_GPIO10] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = stac92hd83xxx_fixup_hp_led_gpio10,
+		.chained = true,
+		.chain_id = STAC_92HD83XXX_HP,
+	},
 	[STAC_92HD83XXX_HEADSET_JACK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = stac92hd83xxx_fixup_headset_jack,
@@ -2702,6 +2720,8 @@
 			  "HP", STAC_92HD83XXX_HP_cNB11_INTQUAD),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1888,
 			  "HP Envy Spectre", STAC_HP_ENVY_BASS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1899,
+			  "HP Folio 13", STAC_HP_LED_GPIO10),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18df,
 			  "HP Folio", STAC_HP_BNB13_EQ),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18F8,
diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c
index 75d0ad5..647a72c 100644
--- a/sound/soc/codecs/88pm860x-codec.c
+++ b/sound/soc/codecs/88pm860x-codec.c
@@ -1328,6 +1328,9 @@
 	pm860x->codec = codec;
 
 	codec->control_data = pm860x->regmap;
+	ret = snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < 4; i++) {
 		ret = request_threaded_irq(pm860x->irq[i], NULL,
diff --git a/sound/soc/codecs/ad1980.c b/sound/soc/codecs/ad1980.c
index 7257a88..34d965a 100644
--- a/sound/soc/codecs/ad1980.c
+++ b/sound/soc/codecs/ad1980.c
@@ -57,8 +57,8 @@
 static const char *ad1980_rec_sel[] = {"Mic", "CD", "NC", "AUX", "Line",
 		"Stereo Mix", "Mono Mix", "Phone"};
 
-static const struct soc_enum ad1980_cap_src =
-	SOC_ENUM_DOUBLE(AC97_REC_SEL, 8, 0, 7, ad1980_rec_sel);
+static SOC_ENUM_DOUBLE_DECL(ad1980_cap_src,
+			    AC97_REC_SEL, 8, 0, ad1980_rec_sel);
 
 static const struct snd_kcontrol_new ad1980_snd_ac97_controls[] = {
 SOC_DOUBLE("Master Playback Volume", AC97_MASTER, 8, 0, 31, 1),
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index f295b65..f4d965ebc 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -1268,11 +1268,23 @@
 	},
 };
 
+static bool da732x_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case DA732X_REG_HPL_DAC_OFF_CNTL:
+	case DA732X_REG_HPR_DAC_OFF_CNTL:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const struct regmap_config da732x_regmap = {
 	.reg_bits		= 8,
 	.val_bits		= 8,
 
 	.max_register		= DA732X_MAX_REG,
+	.volatile_reg		= da732x_volatile,
 	.reg_defaults		= da732x_reg_cache,
 	.num_reg_defaults	= ARRAY_SIZE(da732x_reg_cache),
 	.cache_type		= REGCACHE_RBTREE,
diff --git a/sound/soc/codecs/isabelle.c b/sound/soc/codecs/isabelle.c
index 5839048..cb736dd 100644
--- a/sound/soc/codecs/isabelle.c
+++ b/sound/soc/codecs/isabelle.c
@@ -140,13 +140,17 @@
 static const char *isabelle_rx2_texts[] = {"VRX2", "ARX2"};
 
 static const struct soc_enum isabelle_rx1_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3, 1, isabelle_rx1_texts),
-	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5, 1, isabelle_rx1_texts),
+	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3,
+			ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5,
+			ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts),
 };
 
 static const struct soc_enum isabelle_rx2_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2, 1, isabelle_rx2_texts),
-	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4, 1, isabelle_rx2_texts),
+	SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2,
+			ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4,
+			ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts),
 };
 
 /* Headset DAC playback switches */
@@ -161,13 +165,17 @@
 static const char *isabelle_vtx_texts[] = {"AMIC2", "DMIC"};
 
 static const struct soc_enum isabelle_atx_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7, 1, isabelle_atx_texts),
-	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_atx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0,
+			ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts),
 };
 
 static const struct soc_enum isabelle_vtx_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6, 1, isabelle_vtx_texts),
-	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_vtx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6,
+			ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts),
+	SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0,
+			ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts),
 };
 
 static const struct snd_kcontrol_new atx_mux_controls =
@@ -183,17 +191,13 @@
 /* Left analog microphone selection */
 static const char *isabelle_amic2_texts[] = {"Sub Mic", "Aux/FM Right"};
 
-static const struct soc_enum isabelle_amic1_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 5,
-			ARRAY_SIZE(isabelle_amic1_texts),
-			isabelle_amic1_texts),
-};
+static SOC_ENUM_SINGLE_DECL(isabelle_amic1_enum,
+			    ISABELLE_AMIC_CFG_REG, 5,
+			    isabelle_amic1_texts);
 
-static const struct soc_enum isabelle_amic2_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 4,
-			ARRAY_SIZE(isabelle_amic2_texts),
-			isabelle_amic2_texts),
-};
+static SOC_ENUM_SINGLE_DECL(isabelle_amic2_enum,
+			    ISABELLE_AMIC_CFG_REG, 4,
+			    isabelle_amic2_texts);
 
 static const struct snd_kcontrol_new amic1_control =
 	SOC_DAPM_ENUM("Route", isabelle_amic1_enum);
@@ -206,16 +210,20 @@
 static const char *isabelle_st_voice_texts[] = {"VTX1", "VTX2"};
 
 static const struct soc_enum isabelle_st_audio_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_audio_texts),
 			isabelle_st_audio_texts),
-	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_audio_texts),
 			isabelle_st_audio_texts),
 };
 
 static const struct soc_enum isabelle_st_voice_enum[] = {
-	SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_voice_texts),
 			isabelle_st_voice_texts),
-	SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7, 1,
+	SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7,
+			ARRAY_SIZE(isabelle_st_voice_texts),
 			isabelle_st_voice_texts),
 };
 
diff --git a/sound/soc/codecs/si476x.c b/sound/soc/codecs/si476x.c
index 52e7cb0..fa2b8e0 100644
--- a/sound/soc/codecs/si476x.c
+++ b/sound/soc/codecs/si476x.c
@@ -210,7 +210,7 @@
 static int si476x_codec_probe(struct snd_soc_codec *codec)
 {
 	codec->control_data = dev_get_regmap(codec->dev->parent, NULL);
-	return 0;
+	return snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
 }
 
 static struct snd_soc_dai_ops si476x_dai_ops = {
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index 06edb39..2735361 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -187,42 +187,42 @@
 	13, 16, TLV_DB_SCALE_ITEM(-1500, 300, 0),
 };
 
-static const struct soc_enum sta32x_drc_ac_enum =
-	SOC_ENUM_SINGLE(STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
-			2, sta32x_drc_ac);
-static const struct soc_enum sta32x_auto_eq_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
-			3, sta32x_auto_eq_mode);
-static const struct soc_enum sta32x_auto_gc_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
-			4, sta32x_auto_gc_mode);
-static const struct soc_enum sta32x_auto_xo_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
-			16, sta32x_auto_xo_mode);
-static const struct soc_enum sta32x_preset_eq_enum =
-	SOC_ENUM_SINGLE(STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
-			32, sta32x_preset_eq_mode);
-static const struct soc_enum sta32x_limiter_ch1_enum =
-	SOC_ENUM_SINGLE(STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch2_enum =
-	SOC_ENUM_SINGLE(STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch3_enum =
-	SOC_ENUM_SINGLE(STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
-			3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter1_attack_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxA_SHIFT,
-			16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter2_attack_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxA_SHIFT,
-			16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter1_release_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxR_SHIFT,
-			16, sta32x_limiter_release_rate);
-static const struct soc_enum sta32x_limiter2_release_rate_enum =
-	SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxR_SHIFT,
-			16, sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_drc_ac_enum,
+			    STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
+			    sta32x_drc_ac);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_eq_enum,
+			    STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
+			    sta32x_auto_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_gc_enum,
+			    STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
+			    sta32x_auto_gc_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_xo_enum,
+			    STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
+			    sta32x_auto_xo_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_preset_eq_enum,
+			    STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
+			    sta32x_preset_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch1_enum,
+			    STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch2_enum,
+			    STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch3_enum,
+			    STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
+			    sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_attack_rate_enum,
+			    STA32X_L1AR, STA32X_LxA_SHIFT,
+			    sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_attack_rate_enum,
+			    STA32X_L2AR, STA32X_LxA_SHIFT,
+			    sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_release_rate_enum,
+			    STA32X_L1AR, STA32X_LxR_SHIFT,
+			    sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_release_rate_enum,
+			    STA32X_L2AR, STA32X_LxR_SHIFT,
+			    sta32x_limiter_release_rate);
 
 /* byte array controls for setting biquad, mixer, scaling coefficients;
  * for biquads all five coefficients need to be set in one go,
@@ -331,7 +331,7 @@
 
 static int sta32x_cache_sync(struct snd_soc_codec *codec)
 {
-	struct sta32x_priv *sta32x = codec->control_data;
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
 	unsigned int mute;
 	int rc;
 
@@ -434,7 +434,7 @@
 SOC_ENUM("Limiter1 Attack Rate (dB/ms)", sta32x_limiter1_attack_rate_enum),
 SOC_ENUM("Limiter2 Attack Rate (dB/ms)", sta32x_limiter2_attack_rate_enum),
 SOC_ENUM("Limiter1 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
-SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
+SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter2_release_rate_enum),
 
 /* depending on mode, the attack/release thresholds have
  * two different enum definitions; provide both
diff --git a/sound/soc/codecs/wm8400.c b/sound/soc/codecs/wm8400.c
index 48dc7d2..6d684d9 100644
--- a/sound/soc/codecs/wm8400.c
+++ b/sound/soc/codecs/wm8400.c
@@ -117,19 +117,23 @@
 static const char *wm8400_digital_sidetone[] =
 	{"None", "Left ADC", "Right ADC", "Reserved"};
 
-static const struct soc_enum wm8400_left_digital_sidetone_enum =
-SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE,
-		WM8400_ADC_TO_DACL_SHIFT, 2, wm8400_digital_sidetone);
+static SOC_ENUM_SINGLE_DECL(wm8400_left_digital_sidetone_enum,
+			    WM8400_DIGITAL_SIDE_TONE,
+			    WM8400_ADC_TO_DACL_SHIFT,
+			    wm8400_digital_sidetone);
 
-static const struct soc_enum wm8400_right_digital_sidetone_enum =
-SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE,
-		WM8400_ADC_TO_DACR_SHIFT, 2, wm8400_digital_sidetone);
+static SOC_ENUM_SINGLE_DECL(wm8400_right_digital_sidetone_enum,
+			    WM8400_DIGITAL_SIDE_TONE,
+			    WM8400_ADC_TO_DACR_SHIFT,
+			    wm8400_digital_sidetone);
 
 static const char *wm8400_adcmode[] =
 	{"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"};
 
-static const struct soc_enum wm8400_right_adcmode_enum =
-SOC_ENUM_SINGLE(WM8400_ADC_CTRL, WM8400_ADC_HPF_CUT_SHIFT, 3, wm8400_adcmode);
+static SOC_ENUM_SINGLE_DECL(wm8400_right_adcmode_enum,
+			    WM8400_ADC_CTRL,
+			    WM8400_ADC_HPF_CUT_SHIFT,
+			    wm8400_adcmode);
 
 static const struct snd_kcontrol_new wm8400_snd_controls[] = {
 /* INMIXL */
@@ -422,9 +426,10 @@
 static const char *wm8400_ainlmux[] =
 	{"INMIXL Mix", "RXVOICE Mix", "DIFFINL Mix"};
 
-static const struct soc_enum wm8400_ainlmux_enum =
-SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINLMODE_SHIFT,
-	ARRAY_SIZE(wm8400_ainlmux), wm8400_ainlmux);
+static SOC_ENUM_SINGLE_DECL(wm8400_ainlmux_enum,
+			    WM8400_INPUT_MIXER1,
+			    WM8400_AINLMODE_SHIFT,
+			    wm8400_ainlmux);
 
 static const struct snd_kcontrol_new wm8400_dapm_ainlmux_controls =
 SOC_DAPM_ENUM("Route", wm8400_ainlmux_enum);
@@ -435,9 +440,10 @@
 static const char *wm8400_ainrmux[] =
 	{"INMIXR Mix", "RXVOICE Mix", "DIFFINR Mix"};
 
-static const struct soc_enum wm8400_ainrmux_enum =
-SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINRMODE_SHIFT,
-	ARRAY_SIZE(wm8400_ainrmux), wm8400_ainrmux);
+static SOC_ENUM_SINGLE_DECL(wm8400_ainrmux_enum,
+			    WM8400_INPUT_MIXER1,
+			    WM8400_AINRMODE_SHIFT,
+			    wm8400_ainrmux);
 
 static const struct snd_kcontrol_new wm8400_dapm_ainrmux_controls =
 SOC_DAPM_ENUM("Route", wm8400_ainrmux_enum);
diff --git a/sound/soc/codecs/wm8770.c b/sound/soc/codecs/wm8770.c
index 89a18d8..5bce210 100644
--- a/sound/soc/codecs/wm8770.c
+++ b/sound/soc/codecs/wm8770.c
@@ -196,8 +196,8 @@
 	"AIN5", "AIN6", "AIN7", "AIN8"
 };
 
-static const struct soc_enum ain_enum =
-	SOC_ENUM_DOUBLE(WM8770_ADCMUX, 0, 4, 8, ain_text);
+static SOC_ENUM_DOUBLE_DECL(ain_enum,
+			    WM8770_ADCMUX, 0, 4, ain_text);
 
 static const struct snd_kcontrol_new ain_mux =
 	SOC_DAPM_ENUM("Capture Mux", ain_enum);
diff --git a/sound/soc/codecs/wm8900.c b/sound/soc/codecs/wm8900.c
index e98bc70..43c2201 100644
--- a/sound/soc/codecs/wm8900.c
+++ b/sound/soc/codecs/wm8900.c
@@ -304,53 +304,53 @@
 
 static const char *mic_bias_level_txt[] = { "0.9*AVDD", "0.65*AVDD" };
 
-static const struct soc_enum mic_bias_level =
-SOC_ENUM_SINGLE(WM8900_REG_INCTL, 8, 2, mic_bias_level_txt);
+static SOC_ENUM_SINGLE_DECL(mic_bias_level,
+			    WM8900_REG_INCTL, 8, mic_bias_level_txt);
 
 static const char *dac_mute_rate_txt[] = { "Fast", "Slow" };
 
-static const struct soc_enum dac_mute_rate =
-SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 7, 2, dac_mute_rate_txt);
+static SOC_ENUM_SINGLE_DECL(dac_mute_rate,
+			    WM8900_REG_DACCTRL, 7, dac_mute_rate_txt);
 
 static const char *dac_deemphasis_txt[] = {
 	"Disabled", "32kHz", "44.1kHz", "48kHz"
 };
 
-static const struct soc_enum dac_deemphasis =
-SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 4, 4, dac_deemphasis_txt);
+static SOC_ENUM_SINGLE_DECL(dac_deemphasis,
+			    WM8900_REG_DACCTRL, 4, dac_deemphasis_txt);
 
 static const char *adc_hpf_cut_txt[] = {
 	"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"
 };
 
-static const struct soc_enum adc_hpf_cut =
-SOC_ENUM_SINGLE(WM8900_REG_ADCCTRL, 5, 4, adc_hpf_cut_txt);
+static SOC_ENUM_SINGLE_DECL(adc_hpf_cut,
+			    WM8900_REG_ADCCTRL, 5, adc_hpf_cut_txt);
 
 static const char *lr_txt[] = {
 	"Left", "Right"
 };
 
-static const struct soc_enum aifl_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 15, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(aifl_src,
+			    WM8900_REG_AUDIO1, 15, lr_txt);
 
-static const struct soc_enum aifr_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 14, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(aifr_src,
+			    WM8900_REG_AUDIO1, 14, lr_txt);
 
-static const struct soc_enum dacl_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 15, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(dacl_src,
+			    WM8900_REG_AUDIO2, 15, lr_txt);
 
-static const struct soc_enum dacr_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 14, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(dacr_src,
+			    WM8900_REG_AUDIO2, 14, lr_txt);
 
 static const char *sidetone_txt[] = {
 	"Disabled", "Left ADC", "Right ADC"
 };
 
-static const struct soc_enum dacl_sidetone =
-SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 2, 3, sidetone_txt);
+static SOC_ENUM_SINGLE_DECL(dacl_sidetone,
+			    WM8900_REG_SIDETONE, 2, sidetone_txt);
 
-static const struct soc_enum dacr_sidetone =
-SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 0, 3, sidetone_txt);
+static SOC_ENUM_SINGLE_DECL(dacr_sidetone,
+			    WM8900_REG_SIDETONE, 0, sidetone_txt);
 
 static const struct snd_kcontrol_new wm8900_snd_controls[] = {
 SOC_ENUM("Mic Bias Level", mic_bias_level),
@@ -496,8 +496,8 @@
 
 static const char *wm8900_lp_mux[] = { "Disabled", "Enabled" };
 
-static const struct soc_enum wm8900_lineout2_lp_mux =
-SOC_ENUM_SINGLE(WM8900_REG_LOUTMIXCTL1, 1, 2, wm8900_lp_mux);
+static SOC_ENUM_SINGLE_DECL(wm8900_lineout2_lp_mux,
+			    WM8900_REG_LOUTMIXCTL1, 1, wm8900_lp_mux);
 
 static const struct snd_kcontrol_new wm8900_lineout2_lp =
 SOC_DAPM_ENUM("Route", wm8900_lineout2_lp_mux);
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index b7488f1..d4248e0 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -153,7 +153,7 @@
 
 			data32 &= 0xffffff;
 
-			wm8994_bulk_write(codec->control_data,
+			wm8994_bulk_write(wm8994->wm8994,
 					  data32 & 0xffffff,
 					  block_len / 2,
 					  (void *)(data + 8));
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index b9be9cb..adb7206 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -265,21 +265,21 @@
 	"2.7kHz", "1.35kHz", "675Hz", "370Hz", "180Hz", "90Hz", "45Hz"
 };
 
-static const struct soc_enum sidetone_hpf =
-	SOC_ENUM_SINGLE(WM8994_SIDETONE, 7, 7, sidetone_hpf_text);
+static SOC_ENUM_SINGLE_DECL(sidetone_hpf,
+			    WM8994_SIDETONE, 7, sidetone_hpf_text);
 
 static const char *adc_hpf_text[] = {
 	"HiFi", "Voice 1", "Voice 2", "Voice 3"
 };
 
-static const struct soc_enum aif1adc1_hpf =
-	SOC_ENUM_SINGLE(WM8994_AIF1_ADC1_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif1adc1_hpf,
+			    WM8994_AIF1_ADC1_FILTERS, 13, adc_hpf_text);
 
-static const struct soc_enum aif1adc2_hpf =
-	SOC_ENUM_SINGLE(WM8994_AIF1_ADC2_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif1adc2_hpf,
+			    WM8994_AIF1_ADC2_FILTERS, 13, adc_hpf_text);
 
-static const struct soc_enum aif2adc_hpf =
-	SOC_ENUM_SINGLE(WM8994_AIF2_ADC_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif2adc_hpf,
+			    WM8994_AIF2_ADC_FILTERS, 13, adc_hpf_text);
 
 static const DECLARE_TLV_DB_SCALE(aif_tlv, 0, 600, 0);
 static const DECLARE_TLV_DB_SCALE(digital_tlv, -7200, 75, 1);
@@ -501,39 +501,39 @@
 	"Left", "Right"
 };
 
-static const struct soc_enum aif1adcl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1adcl_src,
+			    WM8994_AIF1_CONTROL_1, 15, aif_chan_src_text);
 
-static const struct soc_enum aif1adcr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1adcr_src,
+			    WM8994_AIF1_CONTROL_1, 14, aif_chan_src_text);
 
-static const struct soc_enum aif2adcl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2adcl_src,
+			    WM8994_AIF2_CONTROL_1, 15, aif_chan_src_text);
 
-static const struct soc_enum aif2adcr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2adcr_src,
+			    WM8994_AIF2_CONTROL_1, 14, aif_chan_src_text);
 
-static const struct soc_enum aif1dacl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1dacl_src,
+			    WM8994_AIF1_CONTROL_2, 15, aif_chan_src_text);
 
-static const struct soc_enum aif1dacr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1dacr_src,
+			    WM8994_AIF1_CONTROL_2, 14, aif_chan_src_text);
 
-static const struct soc_enum aif2dacl_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacl_src,
+			    WM8994_AIF2_CONTROL_2, 15, aif_chan_src_text);
 
-static const struct soc_enum aif2dacr_src =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacr_src,
+			    WM8994_AIF2_CONTROL_2, 14, aif_chan_src_text);
 
 static const char *osr_text[] = {
 	"Low Power", "High Performance",
 };
 
-static const struct soc_enum dac_osr =
-	SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 0, 2, osr_text);
+static SOC_ENUM_SINGLE_DECL(dac_osr,
+			    WM8994_OVERSAMPLING, 0, osr_text);
 
-static const struct soc_enum adc_osr =
-	SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 1, 2, osr_text);
+static SOC_ENUM_SINGLE_DECL(adc_osr,
+			    WM8994_OVERSAMPLING, 1, osr_text);
 
 static const struct snd_kcontrol_new wm8994_snd_controls[] = {
 SOC_DOUBLE_R_TLV("AIF1ADC1 Volume", WM8994_AIF1_ADC1_LEFT_VOLUME,
@@ -690,17 +690,20 @@
 	"30ms", "125ms", "250ms", "500ms",
 };
 
-static const struct soc_enum wm8958_aif1dac1_ng_hold =
-	SOC_ENUM_SINGLE(WM8958_AIF1_DAC1_NOISE_GATE,
-			WM8958_AIF1DAC1_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac1_ng_hold,
+			    WM8958_AIF1_DAC1_NOISE_GATE,
+			    WM8958_AIF1DAC1_NG_THR_SHIFT,
+			    wm8958_ng_text);
 
-static const struct soc_enum wm8958_aif1dac2_ng_hold =
-	SOC_ENUM_SINGLE(WM8958_AIF1_DAC2_NOISE_GATE,
-			WM8958_AIF1DAC2_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac2_ng_hold,
+			    WM8958_AIF1_DAC2_NOISE_GATE,
+			    WM8958_AIF1DAC2_NG_THR_SHIFT,
+			    wm8958_ng_text);
 
-static const struct soc_enum wm8958_aif2dac_ng_hold =
-	SOC_ENUM_SINGLE(WM8958_AIF2_DAC_NOISE_GATE,
-			WM8958_AIF2DAC_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif2dac_ng_hold,
+			    WM8958_AIF2_DAC_NOISE_GATE,
+			    WM8958_AIF2DAC_NG_THR_SHIFT,
+			    wm8958_ng_text);
 
 static const struct snd_kcontrol_new wm8958_snd_controls[] = {
 SOC_SINGLE_TLV("AIF3 Boost Volume", WM8958_AIF3_CONTROL_2, 10, 3, 0, aif_tlv),
@@ -1341,8 +1344,8 @@
 	"DMIC",
 };
 
-static const struct soc_enum adc_enum =
-	SOC_ENUM_SINGLE(0, 0, 2, adc_mux_text);
+static SOC_ENUM_SINGLE_DECL(adc_enum,
+			    0, 0, adc_mux_text);
 
 static const struct snd_kcontrol_new adcl_mux =
 	SOC_DAPM_ENUM_VIRT("ADCL Mux", adc_enum);
@@ -1478,14 +1481,14 @@
 	"ADC/DMIC1", "DMIC2",
 };
 
-static const struct soc_enum sidetone1_enum =
-	SOC_ENUM_SINGLE(WM8994_SIDETONE, 0, 2, sidetone_text);
+static SOC_ENUM_SINGLE_DECL(sidetone1_enum,
+			    WM8994_SIDETONE, 0, sidetone_text);
 
 static const struct snd_kcontrol_new sidetone1_mux =
 	SOC_DAPM_ENUM("Left Sidetone Mux", sidetone1_enum);
 
-static const struct soc_enum sidetone2_enum =
-	SOC_ENUM_SINGLE(WM8994_SIDETONE, 1, 2, sidetone_text);
+static SOC_ENUM_SINGLE_DECL(sidetone2_enum,
+			    WM8994_SIDETONE, 1, sidetone_text);
 
 static const struct snd_kcontrol_new sidetone2_mux =
 	SOC_DAPM_ENUM("Right Sidetone Mux", sidetone2_enum);
@@ -1498,22 +1501,24 @@
 	"None", "ADCDAT",
 };
 
-static const struct soc_enum aif1_loopback_enum =
-	SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, WM8994_AIF1_LOOPBACK_SHIFT, 2,
-			loopback_text);
+static SOC_ENUM_SINGLE_DECL(aif1_loopback_enum,
+			    WM8994_AIF1_CONTROL_2,
+			    WM8994_AIF1_LOOPBACK_SHIFT,
+			    loopback_text);
 
 static const struct snd_kcontrol_new aif1_loopback =
 	SOC_DAPM_ENUM("AIF1 Loopback", aif1_loopback_enum);
 
-static const struct soc_enum aif2_loopback_enum =
-	SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, WM8994_AIF2_LOOPBACK_SHIFT, 2,
-			loopback_text);
+static SOC_ENUM_SINGLE_DECL(aif2_loopback_enum,
+			    WM8994_AIF2_CONTROL_2,
+			    WM8994_AIF2_LOOPBACK_SHIFT,
+			    loopback_text);
 
 static const struct snd_kcontrol_new aif2_loopback =
 	SOC_DAPM_ENUM("AIF2 Loopback", aif2_loopback_enum);
 
-static const struct soc_enum aif1dac_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 0, 2, aif1dac_text);
+static SOC_ENUM_SINGLE_DECL(aif1dac_enum,
+			    WM8994_POWER_MANAGEMENT_6, 0, aif1dac_text);
 
 static const struct snd_kcontrol_new aif1dac_mux =
 	SOC_DAPM_ENUM("AIF1DAC Mux", aif1dac_enum);
@@ -1522,8 +1527,8 @@
 	"AIF2DACDAT", "AIF3DACDAT",
 };
 
-static const struct soc_enum aif2dac_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 1, 2, aif2dac_text);
+static SOC_ENUM_SINGLE_DECL(aif2dac_enum,
+			    WM8994_POWER_MANAGEMENT_6, 1, aif2dac_text);
 
 static const struct snd_kcontrol_new aif2dac_mux =
 	SOC_DAPM_ENUM("AIF2DAC Mux", aif2dac_enum);
@@ -1532,8 +1537,8 @@
 	"AIF2ADCDAT", "AIF3DACDAT",
 };
 
-static const struct soc_enum aif2adc_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 2, 2, aif2adc_text);
+static SOC_ENUM_SINGLE_DECL(aif2adc_enum,
+			    WM8994_POWER_MANAGEMENT_6, 2, aif2adc_text);
 
 static const struct snd_kcontrol_new aif2adc_mux =
 	SOC_DAPM_ENUM("AIF2ADC Mux", aif2adc_enum);
@@ -1542,14 +1547,14 @@
 	"AIF1ADCDAT", "AIF2ADCDAT", "AIF2DACDAT", "Mono PCM",
 };
 
-static const struct soc_enum wm8994_aif3adc_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 3, aif3adc_text);
+static SOC_ENUM_SINGLE_DECL(wm8994_aif3adc_enum,
+			    WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text);
 
 static const struct snd_kcontrol_new wm8994_aif3adc_mux =
 	SOC_DAPM_ENUM("AIF3ADC Mux", wm8994_aif3adc_enum);
 
-static const struct soc_enum wm8958_aif3adc_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 4, aif3adc_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif3adc_enum,
+			    WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text);
 
 static const struct snd_kcontrol_new wm8958_aif3adc_mux =
 	SOC_DAPM_ENUM("AIF3ADC Mux", wm8958_aif3adc_enum);
@@ -1558,8 +1563,8 @@
 	"None", "AIF2ADCL", "AIF2ADCR",
 };
 
-static const struct soc_enum mono_pcm_out_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 9, 3, mono_pcm_out_text);
+static SOC_ENUM_SINGLE_DECL(mono_pcm_out_enum,
+			    WM8994_POWER_MANAGEMENT_6, 9, mono_pcm_out_text);
 
 static const struct snd_kcontrol_new mono_pcm_out_mux =
 	SOC_DAPM_ENUM("Mono PCM Out Mux", mono_pcm_out_enum);
@@ -1569,14 +1574,14 @@
 };
 
 /* Note that these two control shouldn't be simultaneously switched to AIF3 */
-static const struct soc_enum aif2dacl_src_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 7, 2, aif2dac_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacl_src_enum,
+			    WM8994_POWER_MANAGEMENT_6, 7, aif2dac_src_text);
 
 static const struct snd_kcontrol_new aif2dacl_src_mux =
 	SOC_DAPM_ENUM("AIF2DACL Mux", aif2dacl_src_enum);
 
-static const struct soc_enum aif2dacr_src_enum =
-	SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 8, 2, aif2dac_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacr_src_enum,
+			    WM8994_POWER_MANAGEMENT_6, 8, aif2dac_src_text);
 
 static const struct snd_kcontrol_new aif2dacr_src_mux =
 	SOC_DAPM_ENUM("AIF2DACR Mux", aif2dacr_src_enum);
diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c
index 3fde9e4..d163e18 100644
--- a/sound/soc/omap/n810.c
+++ b/sound/soc/omap/n810.c
@@ -305,7 +305,9 @@
 	int err;
 	struct device *dev;
 
-	if (!(machine_is_nokia_n810() || machine_is_nokia_n810_wimax()))
+	if (!of_have_populated_dt() ||
+	    (!of_machine_is_compatible("nokia,n810") &&
+	     !of_machine_is_compatible("nokia,n810-wimax")))
 		return -ENODEV;
 
 	n810_snd_device = platform_device_alloc("soc-audio", -1);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index dc8ff13..b9dc6ac 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1218,7 +1218,7 @@
 			ret = regulator_allow_bypass(w->regulator, false);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
-					 "ASoC: Failed to bypass %s: %d\n",
+					 "ASoC: Failed to unbypass %s: %d\n",
 					 w->name, ret);
 		}
 
@@ -1228,7 +1228,7 @@
 			ret = regulator_allow_bypass(w->regulator, true);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
-					 "ASoC: Failed to unbypass %s: %d\n",
+					 "ASoC: Failed to bypass %s: %d\n",
 					 w->name, ret);
 		}
 
@@ -3210,15 +3210,11 @@
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 	const char *pin = (const char *)kcontrol->private_value;
 
-	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
 	if (ucontrol->value.integer.value[0])
 		snd_soc_dapm_enable_pin(&card->dapm, pin);
 	else
 		snd_soc_dapm_disable_pin(&card->dapm, pin);
 
-	mutex_unlock(&card->dapm_mutex);
-
 	snd_soc_dapm_sync(&card->dapm);
 	return 0;
 }
@@ -3248,7 +3244,7 @@
 			ret = regulator_allow_bypass(w->regulator, true);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
-					 "ASoC: Failed to unbypass %s: %d\n",
+					 "ASoC: Failed to bypass %s: %d\n",
 					 w->name, ret);
 		}
 		break;
@@ -3767,22 +3763,84 @@
 }
 
 /**
+ * snd_soc_dapm_enable_pin_unlocked - enable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Enables input/output pin and its parents or children widgets iff there is
+ * a valid audio route and active audio stream.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				   const char *pin)
+{
+	return snd_soc_dapm_set_pin(dapm, pin, 1);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin_unlocked);
+
+/**
  * snd_soc_dapm_enable_pin - enable pin.
  * @dapm: DAPM context
  * @pin: pin name
  *
  * Enables input/output pin and its parents or children widgets iff there is
  * a valid audio route and active audio stream.
+ *
  * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
  * do any widget power switching.
  */
 int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin)
 {
-	return snd_soc_dapm_set_pin(dapm, pin, 1);
+	int ret;
+
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	ret = snd_soc_dapm_set_pin(dapm, pin, 1);
+
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin);
 
 /**
+ * snd_soc_dapm_force_enable_pin_unlocked - force a pin to be enabled
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Enables input/output pin regardless of any other state.  This is
+ * intended for use with microphone bias supplies used in microphone
+ * jack detection.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+					 const char *pin)
+{
+	struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+
+	if (!w) {
+		dev_err(dapm->dev, "ASoC: unknown pin %s\n", pin);
+		return -EINVAL;
+	}
+
+	dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
+	w->connected = 1;
+	w->force = 1;
+	dapm_mark_dirty(w, "force enable");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin_unlocked);
+
+/**
  * snd_soc_dapm_force_enable_pin - force a pin to be enabled
  * @dapm: DAPM context
  * @pin: pin name
@@ -3797,39 +3855,86 @@
 int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm,
 				  const char *pin)
 {
-	struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+	int ret;
 
-	if (!w) {
-		dev_err(dapm->dev, "ASoC: unknown pin %s\n", pin);
-		return -EINVAL;
-	}
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 
-	dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
-	w->connected = 1;
-	w->force = 1;
-	dapm_mark_dirty(w, "force enable");
+	ret = snd_soc_dapm_force_enable_pin_unlocked(dapm, pin);
 
-	return 0;
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin);
 
 /**
+ * snd_soc_dapm_disable_pin_unlocked - disable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Disables input/output pin and its parents or children widgets.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+				    const char *pin)
+{
+	return snd_soc_dapm_set_pin(dapm, pin, 0);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin_unlocked);
+
+/**
  * snd_soc_dapm_disable_pin - disable pin.
  * @dapm: DAPM context
  * @pin: pin name
  *
  * Disables input/output pin and its parents or children widgets.
+ *
  * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
  * do any widget power switching.
  */
 int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm,
 			     const char *pin)
 {
-	return snd_soc_dapm_set_pin(dapm, pin, 0);
+	int ret;
+
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	ret = snd_soc_dapm_set_pin(dapm, pin, 0);
+
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin);
 
 /**
+ * snd_soc_dapm_nc_pin_unlocked - permanently disable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Marks the specified pin as being not connected, disabling it along
+ * any parent or child widgets.  At present this is identical to
+ * snd_soc_dapm_disable_pin() but in future it will be extended to do
+ * additional things such as disabling controls which only affect
+ * paths through the pin.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm,
+			       const char *pin)
+{
+	return snd_soc_dapm_set_pin(dapm, pin, 0);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin_unlocked);
+
+/**
  * snd_soc_dapm_nc_pin - permanently disable pin.
  * @dapm: DAPM context
  * @pin: pin name
@@ -3845,7 +3950,15 @@
  */
 int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin)
 {
-	return snd_soc_dapm_set_pin(dapm, pin, 0);
+	int ret;
+
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	ret = snd_soc_dapm_set_pin(dapm, pin, 0);
+
+	mutex_unlock(&dapm->card->dapm_mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin);
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 47e1ce7..28522bd 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1989,6 +1989,7 @@
 
 		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
 		if (paths < 0) {
+			dpcm_path_put(&list);
 			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
 					fe->dai_link->name,  "playback");
 			mutex_unlock(&card->mutex);
@@ -2018,6 +2019,7 @@
 
 		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
 		if (paths < 0) {
+			dpcm_path_put(&list);
 			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
 					fe->dai_link->name,  "capture");
 			mutex_unlock(&card->mutex);
@@ -2082,6 +2084,7 @@
 	fe->dpcm[stream].runtime = fe_substream->runtime;
 
 	if (dpcm_path_get(fe, stream, &list) <= 0) {
+		dpcm_path_put(&list);
 		dev_dbg(fe->dev, "ASoC: %s no valid %s route\n",
 			fe->dai_link->name, stream ? "capture" : "playback");
 	}
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 44b0ba4..1bed780 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -883,6 +883,7 @@
 		}
 		break;
 
+	case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */
 	case USB_ID(0x046d, 0x0808):
 	case USB_ID(0x046d, 0x0809):
 	case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index da8b7aa..07b0b75 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -87,8 +87,8 @@
 # We process the rest of the Makefile if this is the final invocation of make
 ifeq ($(skip-makefile),)
 
-srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
-objtree		:= $(CURDIR)
+srctree		:= $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)))
+objtree		:= $(realpath $(CURDIR))
 src		:= $(srctree)
 obj		:= $(objtree)
 
@@ -112,7 +112,7 @@
 
 LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION)
 
-INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES)
+INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index f8465a8..23bd69c 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -418,7 +418,7 @@
 
 __attribute__((constructor)) static void init_preload(void)
 {
-	if (__init_state != done)
+	if (__init_state == done)
 		return;
 
 #ifndef __GLIBC__
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
old mode 100644
new mode 100755
diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h
new file mode 100644
index 0000000..d82b170b
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h
index 4c99fcb..042ee8e 100644
--- a/tools/lib/lockdep/uinclude/linux/rcu.h
+++ b/tools/lib/lockdep/uinclude/linux/rcu.h
@@ -13,4 +13,9 @@
 	return 1;
 }
 
+static inline bool rcu_is_watching(void)
+{
+	return false;
+}
+
 #endif
diff --git a/tools/net/Makefile b/tools/net/Makefile
index 004cd74..ee577ea 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -12,7 +12,7 @@
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2
+bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3c53ec2..02f985f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -113,14 +113,16 @@
 	if (!he)
 		return -ENOMEM;
 
-	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	if (err)
-		goto out;
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
 
-	mx = he->mem_info;
-	err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-	if (err)
-		goto out;
+		mx = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+		if (err)
+			goto out;
+	}
 
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -164,14 +166,18 @@
 		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
 					1, 1, 0);
 		if (he) {
-			bx = he->branch_info;
-			err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
-			if (err)
-				goto out;
+			if (ui__has_annotation()) {
+				bx = he->branch_info;
+				err = addr_map_symbol__inc_samples(&bx->from,
+								   evsel->idx);
+				if (err)
+					goto out;
 
-			err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
-			if (err)
-				goto out;
+				err = addr_map_symbol__inc_samples(&bx->to,
+								   evsel->idx);
+				if (err)
+					goto out;
+			}
 
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -205,7 +211,9 @@
 	if (err)
 		goto out;
 
-	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 out:
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 76cd510..5f989a7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -176,7 +176,7 @@
 {
 	struct annotation *notes;
 	struct symbol *sym;
-	int err;
+	int err = 0;
 
 	if (he == NULL || he->ms.sym == NULL ||
 	    ((top->sym_filter_entry == NULL ||
@@ -190,7 +190,9 @@
 		return;
 
 	ip = he->ms.map->map_ip(he->ms.map, ip);
-	err = hist_entry__inc_addr_samples(he, counter, ip);
+
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6aa6fb6..f954c26 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -825,7 +825,6 @@
 	P_SIGNUM(PIPE);
 	P_SIGNUM(ALRM);
 	P_SIGNUM(TERM);
-	P_SIGNUM(STKFLT);
 	P_SIGNUM(CHLD);
 	P_SIGNUM(CONT);
 	P_SIGNUM(STOP);
@@ -841,6 +840,15 @@
 	P_SIGNUM(IO);
 	P_SIGNUM(PWR);
 	P_SIGNUM(SYS);
+#ifdef SIGEMT
+	P_SIGNUM(EMT);
+#endif
+#ifdef SIGSTKFLT
+	P_SIGNUM(STKFLT);
+#endif
+#ifdef SIGSWI
+	P_SIGNUM(SWI);
+#endif
 	default: break;
 	}
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c48d449..0331ea2 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -478,7 +478,7 @@
 endif
 
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd
+  EXTLIBS += -lbfd -lz -liberty
 endif
 
 ifdef NO_DEMANGLE
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 12e5513..523b7bc 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -121,7 +121,7 @@
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
 test-libbfd.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
 
 test-liberty.bin:
 	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 469eb67..3aa555f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -8,6 +8,8 @@
  */
 
 #include "util.h"
+#include "ui/ui.h"
+#include "sort.h"
 #include "build-id.h"
 #include "color.h"
 #include "cache.h"
@@ -489,7 +491,7 @@
 {
 	struct annotation *notes;
 
-	if (sym == NULL || use_browser != 1 || !sort__has_sym)
+	if (sym == NULL)
 		return 0;
 
 	notes = symbol__annotation(sym);
@@ -1399,3 +1401,8 @@
 {
 	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
 }
+
+bool ui__has_annotation(void)
+{
+	return use_browser == 1 && sort__has_sym;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index b2aef59..56ad4f5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -151,6 +151,8 @@
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void disasm__purge(struct list_head *head);
 
+bool ui__has_annotation(void);
+
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines);
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 45cf10a..dadfa7e 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -87,13 +87,15 @@
 	return num;
 }
 
+typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
+
 /*
  * Find the first set bit in a memory region.
  */
 static inline unsigned long
 find_first_bit(const unsigned long *addr, unsigned long size)
 {
-	const unsigned long *p = addr;
+	long_alias_t *p = (long_alias_t *) addr;
 	unsigned long result = 0;
 	unsigned long tmp;
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c872991..620a198 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1213,7 +1213,7 @@
 		 */
 		thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
 				ip, &al);
-		if (al.sym)
+		if (al.map)
 			goto found;
 	}
 found:
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3e9f336..516d19f 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -151,15 +151,15 @@
 
 		gelf_getshdr(sec, shp);
 		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-		if (!strcmp(name, str)) {
+		if (str && !strcmp(name, str)) {
 			if (idx)
 				*idx = cnt;
-			break;
+			return sec;
 		}
 		++cnt;
 	}
 
-	return sec;
+	return NULL;
 }
 
 #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a9d758a..e89afc0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1336,6 +1336,8 @@
 
 			if (syms_ss && runtime_ss)
 				break;
+		} else {
+			symsrc__destroy(ss);
 		}
 
 	}
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index d664182..aa290c0 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -201,6 +201,7 @@
 
 	msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666);
 	if (msgque.msq_id == -1) {
+		err = -errno;
 		printf("Can't create queue\n");
 		goto err_out;
 	}